Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
The following NON-FINAL Office Action is in response to application 18/499,921 filed on 11/01/2023. This communication is the first action on the merits.
Status of Claims
Claims 1-20 are currently pending and have been rejected as follows.
Drawings
The drawings filed on 11/01/2023 are accepted.
Objections
Claim 1 lines 11-12 recite: “and in response determining” which should read “and in response to determining.”
For compact prosecution, in light of the specification, the examiner is interpreting the claim limitation as a step of determining whether or not the updated estimated wear level of the at least one undercarriage component exceeds a wear level threshold.
Claim Rejections - 35 USC § 112(b)
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-6 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claim 1, the claim limitation “recursively receive updated machine signal data”. However, the written description fails to clearly link the “updated data” to a first set of data in that there is no prior mentioning of machine signal data. In other words, it is unclear where the “updated” machine signal data came from. Therefore, the claim is indefinite and is rejected under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph.
For the purpose of compact prosecution, the examiner is interpreting “recursively receiving updated machine signal data” as part of the of the recursive data gathering process given that recursive data collection is assumed to feed back into itself and newly gathered data is used in the next data gathering cycle, and so on, thus yielding “updated” machine signal data.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more. A subject matter eligibility analysis is set forth below. See MPEP 2106.
Representative claim 1 recites:
A system for monitoring an undercarriage of a track-type machine,
the system comprising at least one computer-readable memory and at least one processor communicatively coupled to the at least one computer-readable memory and operative to:
access a reduced order model (ROM) corresponding to the track-type machine; recursively receive updated machine signal data generated by the track-type machine;
in response to receiving the updated machine signal data generated by the track
type machine, recursively generate an updated estimated wear level of at least one undercarriage component of the track-type machine by submitting the updated machine signal data into the ROM;
recursively compare the updated estimated wear level of the at least one
undercarriage component to a wear level threshold;
and in response determining that the updated estimated wear level of the at
least one undercarriage component exceeds the wear level threshold, cause a control interface associated with the track-type machine to deliver a warning notification.
The claim limitations in the abstract idea have been highlighted in bold; the remaining claim limitations are “additional elements.”
Similar limitations comprise the abstract ideas of claims 7 which recites:
A computer-implemented method for monitoring an undercarriage of a track-type machine, the method comprising:
accessing, by at least one processor, a physics-based reduced order model (ROM) corresponding to the track-type machine,
wherein the physics-based ROM is configured to apply one or more physics-based equations to simulate one or more aspects of the track-type machine;
receiving, by the at least one processor, an estimated wear level of at least one undercarriage component of a track-type machine;
receiving, by the at least one processor, machine signal data generated by the track-type machine;
receiving, by the at least one processor, environmental data associated with the track-type machine;
generating, by the at least one processor, an updated estimated wear level of the at least one undercarriage component by submitting the estimated wear level of the at least one undercarriage component, the machine signal data generated by the track-type machine, and the environmental data associated with the track-type machine to the physics-based ROM;
and comparing, by the at least one processor, the updated estimated wear level of the at least one undercarriage component to a wear level threshold,
wherein the at least one processor is configured to, in response to determining that the updated estimated wear level of the at least one undercarriage component exceeds the wear level threshold, cause a control interface associated with the track-type machine to output a warning notification.
Similar limitations comprise the abstract ideas of claims 14 which recites:
A computer-implemented method for monitoring an undercarriage of a track-type machine, the method comprising:
accessing, by at least one processor, a reduced order model (ROM) corresponding to the track-type machine;
receiving, by the at least one processor, an estimated wear level of at least one undercarriage component of a track-type machine;
receiving, by the at least one processor, machine signal data generated by the track-type machine;
generating, by the at least one processor, an updated estimated wear level of the at least one undercarriage component by submitting the estimated wear level of the at least one undercarriage component and the machine signal data generated by the track-type machine to the ROM;
and comparing, by the at least one processor, the updated estimated wear level of the at least one undercarriage component to a wear level threshold,
wherein the at least one processor is configured to, in response to determining that the updated estimated wear level of the at least one undercarriage component exceeds the wear level threshold, causing a control interface associated with the track-type machine to output a warning notification.
Under Step 1 of the analysis, claim 1 does belong to a statutory category, namely it is a machine claim. Likewise, claim 7 is a process claim, and claim 14 is a process claim.
Under Step 2A, Prong One: This part of the eligibility analysis evaluates whether the claim recites a judicial exception. As explained in MPEP 2106.04, subsection II, a claim “recites” a judicial exception when the judicial exception is “set forth” or “described” in the claim.
Under Step 2A, Prong One, the broadest reasonable interpretation consistent with the specification of the steps recited in Claim 1 include at least one judicial exception, that being a mental process.
This can be seen in the claim limitations of “recursively compare” the updated estimated wear level of the at least one undercarriage component to a wear level threshold as well as and in response “determining” that the updated estimated wear level of the at least one undercarriage component exceeds the wear level threshold where the IWIS “compares the updated estimated wear level to a wear level threshold. If the updated estimated wear level exceeds the wear level threshold…after a subsequent interval of time (i.e., interval k+1)…the IWIS then generates a warning notification…” where (see para. 0032 of instant specification) “an estimated wear level of an undercarriage component may be generated or expressed in terms of how distorted the shape of the undercarriage component has become when compared to the originally specified shape of the undercarriage component. Or, for example, in some instances, an estimated wear level of an undercarriage component may be generated or expressed in terms of how much volume the undercarriage component has lost when compared to the originally specified volume of the undercarriage component (e.g., percent volume lost)” and where, for example, (see para. 0036 of instant specification) “a near-failure threshold for a sprocket of a particular undercarriage may be 70% volume lost, while a near-failure threshold for a track shoe may be 80% volume lost.”
These processes of “recursively comparing” and in response “determining” involve mental processes in that these steps can reasonably be completed through observation and evaluation within the human mind. Specifically, observing how distorted the shape of the undercarriage component has become when compared to the originally specified shape of the undercarriage component is an observation that can be done within the human mind. Furthermore, calculating percent volume lost, can reasonably completed within the human mind with the aid of pen and paper, although time consuming. For these reasons, the claim limitations described above qualify as mental processes.
Claims 7 and 14 recites analogous abstract ideas, and thus those claim limitations are rejected for similar reasons as described in the analysis of claim 1.
Step 2A, Prong Two of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception(s) into a practical application of the exception. This evaluation is performed by (a) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (b) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application. 2019 PEG Section III(A)(2), 84 Fed. Reg. at 54-55.
The additional elements in the preamble are recited in generality and represent insignificant extra-solution activity (field-of-use limitations) that is not meaningful to indicate a practical application.
Claim 1 recites the following additional elements: “accessing” a reduced-order model (ROM), recursively “receiving” updated machine signal data, and recursively “generating” an updated estimated wear level by “submitting” the updated machine signal data into the ROM. However, these elements are found to be data gathering/output steps, which are recited at a high level of generality, and thus merely amount to “insignificant extra-solution” activity(ies). See MPEP 2106.05(g) “Insignificant Extra-Solution Activity.”
Under Step 2B, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements, as described above with respect to Step 2A Prong 2. The abstract ideas do not amount to significantly more given that the additional elements merely involve insignificant extra-solution activit(ies). Such insignificant extra-solution activity, e.g. data gathering and output, when re-evaluated under Step 2B is further found to be well-understood, routine, and conventional as evidenced by MPEP 2106.05(d)(II) (describing conventional activities that include transmitting and receiving data over a communication network).
For example, [Lin: Abstract]: Lin uses reduced order modeling to model “aero-hydro-servo-elastic (AHSE) dynamics of each wind turbine… where a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure” is used. [p.2, para. 2, lines 15-17]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others.” [Lin: Abstract]: “This paper developed a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure, having a lower computational cost and therefore more easily scalable.”
[Rodrigo: Abstract]: “A very fast reduced order model is developed to monitor aeroengines condition (defining their degradation from a baseline state) in real time…Thus, the method synergically combines the advantages of data-driven (fast online operation) and model-based (the engine physics is accounted for) condition monitoring methods.”
Claims 7 and 14 recites analogous additional elements, and thus those claim limitations are rejected for similar reasons as described in the analysis of claim 1.
Claim 7 also specifically recites:
“receiving,” by the at least one processor, an estimated wear level of at least one undercarriage component of a track-type machine; “receiving,” by the at least one processor, machine signal data generated by the track-type machine; “receiving,” by the at least one processor, environmental data associated with the track-type machine; “generating,” by the at least one processor, an updated estimated wear level of the at least one undercarriage component by “submitting” the estimated wear level of the at least one undercarriage component, the machine signal data generated by the track-type machine, and the environmental data associated with the track-type machine to the physics-based ROM… However, these elements are found to be data gathering/output steps, which are recited at a high level of generality, and thus merely amount to “insignificant extra-solution” activity(ies). See MPEP 2106.05(g) “Insignificant Extra-Solution Activity.”
Under Step 2B, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements, as described above with respect to Step 2A Prong 2. The abstract ideas do not amount to significantly more given that the additional elements merely involve insignificant extra-solution activit(ies). Such insignificant extra-solution activity, e.g. data gathering and output, when re-evaluated under Step 2B is further found to be well-understood, routine, and conventional as evidenced by MPEP 2106.05(d)(II) (describing conventional activities that include transmitting and receiving data over a communication network).
Claim 14 recites analogous additional elements, and thus those claim limitations are rejected for similar reasons as described in the analysis of claims 1 and 7.
Thus, under Step 2A, prong 2 of the analysis, even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application and the claim is directed to the judicial exception. No specific practical application is associated with the claimed process. For instance, nothing is done after the monitoring of the undercarriage of the track-type machine.
Therefore, similarly the combination and arrangement of the above identified additional elements when analyzed under Step 2B also fails to necessitate a conclusion that claim 1, as well as claims 7 and 14, amount to significantly more than the abstract idea.
With regards to the dependent claims, claims 2-3, 6, 8-9, 12-13 and 15-18 provide additional features/steps which are part of an expanded abstract idea of the independent claim (additionally comprising abstract idea steps) and, therefore, these claims are not eligible without meaningful additional elements that reflect a practical application and/or additional elements that qualify for significantly more for substantially similar reasons as discussed with regards to Claim 1.
Regarding claims 4, 10, and 19, the claims specifically recite: Generating “an estimate of when the undercarriage component will need to be replaced and cause the control interface to output the estimate.” Similarly, claims 5, 11 and 20 recite: “…in response to determining that the updated estimated wear level of the at least one undercarriage component exceeds the failure threshold, cause the control interface to output an indication that the at least one undercarriage component needs to be replaced.” (See para. 0033 of instant specification) where “an updated estimated wear level exceeding the near-failure threshold is an indication that the undercarriage component will soon need to be repaired or replaced… the IWIS can generate a warning notification indicating that the undercarriage component will soon need to be repaired or replaced and deliver the warning notification to a control interface associated with the undercarriage’s machine.”
The determination of an updated estimated wear level exceeding a near-failure threshold and the corresponding warning notification displayed on a control interface are merely viewed as data gathering and output steps, which under Step 2B, do not qualify as additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements, as described above with respect to Step 2A Prong 2. The abstract ideas do not amount to significantly more given that the additional elements merely involve insignificant extra-solution activit(ies). Such insignificant extra-solution activity, e.g. data gathering and output, when re-evaluated under Step 2B is further found to be well-understood, routine, and conventional as evidenced by MPEP 2106.05(d)(II) (describing conventional activities that include transmitting and receiving data over a communication network).
For example, Zhang [0060]: “Based on the predicted wear rate and/or wear of the one or more components, machine learning model 230 may predict a date and/or a time when the one or more components are to be replaced and/or repaired.”
Laperle [0127]: “Once the information is received, the organization can schedule maintenance of the vehicle at step 1303, and subsequently replace or repair the track system component. Accordingly, track system component maintenance operations can be initiated and scheduled without the need for input from the vehicle operator.”
Thus, under Step 2A, prong 2 of the analysis, even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application and the claim is directed to the judicial exception. No specific practical application is associated with the claimed process. For instance, nothing is done once the updated estimated wear level exceeds a near-failure threshold and the corresponding warning notification is displayed on a control interface.
Therefore, similarly the combination and arrangement of the above identified additional elements when analyzed under Step 2B also fails to necessitate a conclusion that claims 4, 10, and 19, as well as claims 5, 11 and 20, amount to significantly more than the abstract idea.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103, which forms the basis for all obviousness rejections set forth in this Office Action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang, US 2022/0139117 A1 (hereinafter “Zhang”), in view of Niedfeldt, P. C., Ingersoll, K., & Beard, R. W. (2017), Comparison and Analysis of Recursive-RANSAC for Multiple Target Tracking: IEEE Transactions on Aerospace and Electronic Systems, 53(1), 461–476. https://doi.org/10.1109/taes.2017.2650818, (hereinafter “Niedfeldt”), further in view of Lin, Z., Cevasco, D., & Collu, M. (2020), A methodology to develop reduced-order models to support the operation and maintenance of offshore wind turbines, Applied Energy, 259, 114228 https://doi.org/10.1016/j.apenergy.2019.114228, (hereinafter “Lin”).
Regarding claim 1, Zhang teaches [Abstract]: a system for monitoring an undercarriage of a track-type machine, the system comprising at least one computer-readable memory and at least one processor communicatively coupled to the at least one computer-readable memory and operative to: [0041]: “Memory 250 includes a random-access memory (RAM), a read only memory (ROM), and/or another type of dynamic or static storage device…that stores information and/or instructions for use by a processor 240 to perform a function.” [0042]: “Wear detection device 190 may include one or more devices (e.g., a server device or a group of server devices) configured to train machine learning model 230 to predict the amount of wear of the one or more components of the undercarriage…and may be implemented by one or more computing resources of a cloud computing environment.” [0008]: “A machine includes one or more memories; and one or more processors configured to: receive, from one or more sensor devices of the machine, sensor data associated with wear of one or more components of an undercarriage of the machine; predict, using a machine learning model and the sensor data, an amount wear of the one or more components based on a wear rate of the one or more components, wherein the machine learning model is trained, using training data, to predict the wear rate of the one or more components, wherein the training data includes two or more of: historical sensor data, historical inspection data, or simulation data, of a simulation model, from one or more third devices, and wherein the two or more of the historical sensor data, the historical inspection data, or the simulation data are associated with wear of the one or more components; and perform an action based on the amount of wear of the one or more components.”
access a…model corresponding to the track-type machine; [0086]: “As further shown in FIG. 3, process 300 may include predicting, using the machine learning model and based on the sensor data, the remaining life of the one or more components (block 350). For example, the first device may predict, using the machine learning model and based on the sensor data, the remaining life of the one or more components”, …receive…machine signal data generated by the track-type machine; in response to receiving the…machine signal data generated by the track-type machine, …generate an…estimated wear level of at least one undercarriage component of the track-type machine by submitting the…machine signal data into the…model; [0008]: “A machine includes one or more memories; and one or more processors configured to: receive, from one or more sensor devices of the machine, sensor data associated with wear of one or more components of an undercarriage of the machine; predict, using a machine learning model and the sensor data, an amount wear of the one or more components based on a wear rate of the one or more components, wherein the machine learning model is trained, using training data, to predict the wear rate of the one or more components, wherein the training data includes two or more of: historical sensor data, historical inspection data, or simulation data, of a simulation model, from one or more third devices, and wherein the two or more of the historical sensor data, the historical inspection data, or the simulation data are associated with wear of the one or more components; and perform an action based on the amount of wear of the one or more components”, …compare the… estimated wear level of the at least one undercarriage component to a wear level threshold; and in response determining that the…estimated wear level of the at least one undercarriage component exceeds the wear level threshold, cause a control interface associated with the track-type machine to deliver a warning notification; [0072]: “Wear detection device 190 may transmit the remaining life information…[0070]: when the amount of wear (of the one or more components) satisfies a threshold amount of wear…[0072]: to cause the one or more devices (e.g., controller 140) to cause machine 105 to… cause an alarm to be activated. The alarm may indicate that the one or more components are to be repaired or replaced.”
[0030]: “Additionally, or alternatively, sensor system 120 may provide the historical sensor data to wear detection device 190 (e.g., to train machine learning model 230) based on a triggering event (e.g., a request from wear detection device 190, a request from controller 140, and/or a request from an operator of machine 105 (e.g., via the integrated display and/or operator controls)…where [0040] the “controller may include one or more processors…capable of being programmed to perform a function.”
[Claim 12] “…the one or more processors are further configured to: cause an operation of the machine to be adjusted based on the amount of wear of the one or more components; transmit remaining life information to a first device to cause the first device to generate, based on the amount of wear of the one or more components, a service request to at least one of repair or replace the one or more components, wherein the remaining life information indicates the amount of wear of the one or more components; or transmit the remaining life information, to a second device associated with an operator of the machine, to cause the operator to adjust the operation of the machine based on the remaining life information or to transmit the service request using the second device associated with the operator.”
However, Zhang does not teach using recursiveness in updating…data and submitting data to a reduced order model (ROM) to recursively update state estimates using sequential measurements.
Niedfeldt teaches a model to recursively update state estimates using sequential measurements [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to use recursiveness in updating…data to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Lin teaches the reduced order model through the modeling of [Lin: Abstract]: “aero-hydro-servo-elastic (AHSE) dynamics of each wind turbine… where a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure” is used. [p.2, para. 2, lines 15-17]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others.”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt, further in view of Lin to use a reduced order model (ROM) because the ROM has a lower computational cost and it is more easily scalable. [Lin: Abstract]: “This paper developed a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure, having a lower computational cost and therefore more easily scalable.” [p.2]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others.”
Regarding claim 2, Zhang teaches the system of claim 1, wherein accessing the…model corresponding to the track-type machine further comprises accessing…a model…, wherein the…model…is configured to…simulate one or more aspects of the track-type machine; [0086]: “As further shown in FIG. 3, process 300 may include predicting, using the machine learning model and based on the sensor data, the remaining life of the one or more components (block 350). For example, the first device may predict, using the machine learning model and based on the sensor data, the remaining life of the one or more components” [0008] “wherein the machine learning model is trained using… simulation data, of a simulation model… associated with wear of the one or more components.”
However, Zhang does not teach the ROM, physics-based ROM and the physics-based ROM configured to apply one or more physics-based equations.
Lin teaches the physics-based reduced order model configured to apply one or more physics-based equations through the modeling of [Lin: Abstract]: “aero-hydro-servo-elastic (AHSE) dynamics of each wind turbine… where a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure” is used. [p.2]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others.” [p.2]: “All the above ROMs focus on the reduction of the system’s mass and stiffness matrix, derived from the linearization of the system equations of motion.”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use a physics-based ROM configured to apply one or more physics-based equations due to their lower computational cost, easy scalability and effectiveness in monitoring the physics of wear. [Lin: Abstract]: “This paper developed a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure, having a lower computational cost and therefore more easily scalable.” [p.2]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others…All the above ROMs focus on the reduction of the system’s mass and stiffness matrix, derived from the linearization of the system equations of motion.”
Regarding claim 3, Zhang teaches the system of claim 1, wherein the at least one processor is further operative to [0041]: “Memory 250 includes a random-access memory (RAM), a read only memory (ROM), and/or another type of dynamic or static storage device…that stores information and/or instructions for use by a processor 240 to perform a function”, …receive…environmental data associated with the track-type machine; [0043]: “The historical inspection data may include…environmental conditions at a location associated with machine” and wherein …generating the…estimated wear level of the at least one undercarriage component further comprises submitting the…environmental data associated with the track-type machine and the…estimated wear level of the at least one undercarriage component to the…model; [0008]: “A machine includes one or more memories; and one or more processors configured to: receive, from one or more sensor devices of the machine, sensor data associated with wear of one or more components of an undercarriage of the machine; predict, using a machine learning model and the sensor data, an amount wear of the one or more components based on a wear rate of the one or more components, wherein the machine learning model is trained, using training data, to predict the wear rate of the one or more components, wherein the training data includes two or more of: historical sensor data, historical inspection data, or simulation data, of a simulation model, from one or more third devices, and wherein the two or more of the historical sensor data, the historical inspection data, or the simulation data are associated with wear of the one or more components; and perform an action based on the amount of wear of the one or more components.”
[Claim 12] “…the one or more processors are further configured to: cause an operation of the machine to be adjusted based on the amount of wear of the one or more components; transmit remaining life information to a first device to cause the first device to generate, based on the amount of wear of the one or more components, a service request to at least one of repair or replace the one or more components, wherein the remaining life information indicates the amount of wear of the one or more components; or transmit the remaining life information, to a second device associated with an operator of the machine, to cause the operator to adjust the operation of the machine based on the remaining life information or to transmit the service request using the second device associated with the operator.”
However, Zhang does not teach using recursiveness in updating…data and using a ROM to recursively update state estimates using sequential measurements.
Niedfeldt teaches a model to recursively update state estimates using sequential measurements; [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to use recursiveness in updating…data to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Lin is directed to providing a methodology to develop reduced-order models to support the operation and maintenance of offshore wind turbines. Therein Lin teaches the reduced order model through the modeling of [Lin: Abstract]: “aero-hydro-servo-elastic (AHSE) dynamics of each wind turbine… where a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure” is used. [p.2, para. 2, lines 15-17]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others.”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt further in view of Lin to use a reduced order model (ROM) because the ROM has a lower computational cost and it is more easily scalable. [Lin: Abstract]: “This paper developed a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure, having a lower computational cost and therefore more easily scalable.” [p.2]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others.”
Regarding claim 4, Zhang teaches the system of claim 1 wherein: …comparing the…estimated wear level of the at least one undercarriage component to the wear level threshold further comprises comparing the… estimated wear level to a near-failure threshold;
[0070]: “Wear detection device 190 may transmit the remaining life information when the amount of wear (of the one or more components) satisfies a threshold amount of wear. The remaining life information may indicate the amount of wear of the one or more components, indicate a wear rate of the one or more components, indicate the remaining life of the one or more components, and/or an offer associated with repairing and/or replacing the one or more components,” and [0076]: “wear detection device 190 may determine whether a failure of the one or more components is imminent (e.g., based on the predicted component wear information). If wear detection device 190 determines that the failure is imminent, wear detection device 190 may perform one or more of the actions described above. If wear detection device 190 determines that the failure is not imminent, wear detection device 190 may not perform an action”, and the at least one processor is further operative to, in response to determining that the…estimated wear level of the at least one undercarriage component exceeds the near-failure threshold, generate an estimate of when the undercarriage component will need to be replaced and cause the control interface to output the estimate; [Claim 12] “…the one or more processors are further configured to: cause an operation of the machine to be adjusted based on the amount of wear of the one or more components; transmit remaining life information to a first device to cause the first device to generate, based on the amount of wear of the one or more components, a service request to at least one of repair or replace the one or more components, wherein the remaining life information indicates the amount of wear of the one or more components; or transmit the remaining life information, to a second device associated with an operator of the machine, to cause the operator to adjust the operation of the machine based on the remaining life information or to transmit the service request using the second device associated with the operator.” [0030]: “Additionally, or alternatively, sensor system 120 may provide the historical sensor data to wear detection device 190 (e.g., to train machine learning model 230) based on a triggering event (e.g., a request from wear detection device 190, a request from controller 140, and/or a request from an operator of machine 105 (e.g., via the integrated display and/or operator controls)…where [0040] the “controller may include one or more processors…capable of being programmed to perform a function.”
However, Zhang does not teach using recursiveness in updating…data.
Niedfeldt teaches a model to recursively update state estimates using sequential measurements [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to use recursiveness in updating…data to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Regarding claim 5, Zhang teaches the system of claim 1, wherein: …comparing the…estimated wear level of the at least one undercarriage component to the wear level threshold further comprises comparing the…estimated wear level to a failure threshold; [0070]: “Wear detection device 190 may transmit the remaining life information when the amount of wear (of the one or more components) satisfies a threshold amount of wear. The remaining life information may indicate the amount of wear of the one or more components, indicate a wear rate of the one or more components, indicate the remaining life of the one or more components, and/or an offer associated with repairing and/or replacing the one or more components,” and [0076]: “wear detection device 190 may determine whether a failure of the one or more components is imminent (e.g., based on the predicted component wear information). If wear detection device 190 determines that the failure is imminent, wear detection device 190 may perform one or more of the actions described above. If wear detection device 190 determines that the failure is not imminent, wear detection device 190 may not perform an action”, and the at least one processor is further operative to, in response to determining that the…estimated wear level of the at least one undercarriage component exceeds the failure threshold, cause the control interface to output an indication that the at least one undercarriage component needs to be replaced; [Claim 12]: “…the one or more processors are further configured to: cause an operation of the machine to be adjusted based on the amount of wear of the one or more components; transmit remaining life information to a first device to cause the first device to generate, based on the amount of wear of the one or more components, a service request to at least one of repair or replace the one or more components, wherein the remaining life information indicates the amount of wear of the one or more components; or transmit the remaining life information, to a second device associated with an operator of the machine, to cause the operator to adjust the operation of the machine based on the remaining life information or to transmit the service request using the second device associated with the operator.”
[0030]: “Additionally, or alternatively, sensor system 120 may provide the historical sensor data to wear detection device 190 (e.g., to train machine learning model 230) based on a triggering event (e.g., a request from wear detection device 190, a request from controller 140, and/or a request from an operator of machine 105 (e.g., via the integrated display and/or operator controls)…where [0040] the “controller may include one or more processors…capable of being programmed to perform a function.”
However, Zhang does not teach using recursiveness in updating…data.
Niedfeldt teaches a model to recursively update state estimates using sequential measurements [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to use recursiveness in updating…data to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Regarding claim 6, Zhang teaches the system of claim 1, wherein the at least one processor is further operative to prompt the control interface to display the warning notification within an interface built into the track-type machine; [Claim 12]: “…the one or more processors are further configured to: cause an operation of the machine to be adjusted based on the amount of wear of the one or more components; transmit remaining life information to a first device to cause the first device to generate, based on the amount of wear of the one or more components, a service request to at least one of repair or replace the one or more components, wherein the remaining life information indicates the amount of wear of the one or more components; or transmit the remaining life information, to a second device associated with an operator of the machine, to cause the operator to adjust the operation of the machine based on the remaining life information or to transmit the service request using the second device associated with the operator.” [0030]: “Additionally, or alternatively, sensor system 120 may provide the historical sensor data to wear detection device 190 (e.g., to train machine learning model 230) based on a triggering event (e.g., a request from wear detection device 190, a request from controller 140, and/or a request from an operator of machine 105 (e.g., via the integrated display and/or operator controls)…where [0040] the “controller may include one or more processors…capable of being programmed to perform a function.” [0072]: “Wear detection device 190 may transmit the remaining life information…[0070]: when the amount of wear (of the one or more components) satisfies a threshold amount of wear…[0072]: to cause the one or more devices (e.g., controller 140) to cause machine 105 to… cause an alarm to be activated. The alarm may indicate that the one or more components are to be repaired or replaced.”
Regarding claim 7, Zhang teaches a computer-implemented method for monitoring an undercarriage of a track-type machine, the method comprising:
[0041]: “Memory 250 includes a random-access memory (RAM), a read only memory (ROM), and/or another type of dynamic or static storage device…that stores information and/or instructions for use by a processor 240 to perform a function.” [0042]: “Wear detection device 190 may include one or more devices (e.g., a server device or a group of server devices) configured to train machine learning model 230 to predict the amount of wear of the one or more components of the undercarriage… and may be implemented by one or more computing resources of a cloud computing environment”, accessing, by at least one processor, a…model corresponding to the track-type machine is configured to…simulate one or more aspects of the track-type machine; receiving, by the at least one processor, an estimated wear level of at least one undercarriage component of a track-type machine; receiving, by the at least one processor, machine signal data generated by the track-type machine; [0086]: “As further shown in FIG. 3, process 300 may include predicting, using the machine learning model and based on the sensor data, the remaining life of the one or more components (block 350). For example, the first device may predict, using the machine learning model and based on the sensor data, the remaining life of the one or more components.” [0008]: “A machine includes one or more memories; and one or more processors configured to: receive, from one or more sensor devices of the machine, sensor data associated with wear of one or more components of an undercarriage of the machine; predict, using a machine learning model and the sensor data, an amount wear of the one or more components based on a wear rate of the one or more components, wherein the machine learning model is trained, using training data, to predict the wear rate of the one or more components, wherein the training data includes two or more of: historical sensor data, historical inspection data, or simulation data, of a simulation model, from one or more third devices, and wherein the two or more of the historical sensor data, the historical inspection data, or the simulation data are associated with wear of the one or more components; and perform an action based on the amount of wear of the one or more components”, receiving, by the at least one processor, environmental data associated with the track-type machine; [0043]: “The historical inspection data may include…environmental conditions at a location associated with machine.” [0008]: “A machine includes one or more memories; and one or more processors configured to: receive, from one or more sensor devices of the machine, sensor data associated with wear of one or more components of an undercarriage of the machine; predict, using a machine learning model and the sensor data, an amount wear of the one or more components based on a wear rate of the one or more components, wherein the machine learning model is trained, using training data, to predict the wear rate of the one or more components, wherein the training data includes two or more of: historical sensor data, historical inspection data, or simulation data, of a simulation model, from one or more third devices, and wherein the two or more of the historical sensor data, the historical inspection data, or the simulation data are associated with wear of the one or more components; and perform an action based on the amount of wear of the one or more components”, generating, by the at least one processor, an…estimated wear level of the at least one undercarriage component by submitting the estimated wear level of the at least one undercarriage component, the machine signal data generated by the track-type machine, and the environmental data associated with the track-type machine to the…model; [Claim 12] “…the one or more processors are further configured to: cause an operation of the machine to be adjusted based on the amount of wear of the one or more components; transmit remaining life information to a first device to cause the first device to generate, based on the amount of wear of the one or more components, a service request to at least one of repair or replace the one or more components, wherein the remaining life information indicates the amount of wear of the one or more components; or transmit the remaining life information, to a second device associated with an operator of the machine, to cause the operator to adjust the operation of the machine based on the remaining life information or to transmit the service request using the second device associated with the operator”, [0008]: “A machine includes one or more memories; and one or more processors configured to: receive, from one or more sensor devices of the machine, sensor data associated with wear of one or more components of an undercarriage of the machine; predict, using a machine learning model and the sensor data, an amount wear of the one or more components based on a wear rate of the one or more components, wherein the machine learning model is trained, using training data, to predict the wear rate of the one or more components, wherein the training data includes two or more of: historical sensor data, historical inspection data, or simulation data, of a simulation model, from one or more third devices, and wherein the two or more of the historical sensor data, the historical inspection data, or the simulation data are associated with wear of the one or more components; and perform an action based on the amount of wear of the one or more components”, and comparing, by the at least one processor, the…estimated wear level of the at least one undercarriage component to a wear level threshold, wherein the at least one processor is configured to, in response to determining that the…estimated wear level of the at least one undercarriage component exceeds the wear level threshold, cause a control interface associated with the track-type machine to output a warning notification; [0030]: “Additionally, or alternatively, sensor system 120 may provide the historical sensor data to wear detection device 190 (e.g., to train machine learning model 230) based on a triggering event (e.g., a request from wear detection device 190, a request from controller 140, and/or a request from an operator of machine 105 (e.g., via the integrated display and/or operator controls)…where [0040] the “controller may include one or more processors…capable of being programmed to perform a function.” [0072]: “Wear detection device 190 may transmit the remaining life information…[0070]: when the amount of wear (of the one or more components) satisfies a threshold amount of wear…[0072]: to cause the one or more devices (e.g., controller 140) to cause machine 105 to… cause an alarm to be activated. The alarm may indicate that the one or more components are to be repaired or replaced.”
Zhang does not teach updating…data, and Zhang does not teach the physics-based reduced order model… wherein the physics-based ROM is configured to apply one or more physics-based equations.
Niedfeldt teaches a model to recursively update state estimates using sequential measurements [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to use updated data to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Lin teaches the physics-based reduced order model…wherein the physics-based ROM is configured to apply one or more physics-based equations through the modeling of [Lin: Abstract]: “aero-hydro-servo-elastic (AHSE) dynamics of each wind turbine… where a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure” is used. [p.2]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others.” [p.2]: “All the above ROMs focus on the reduction of the system’s mass and stiffness matrix, derived from the linearization of the system equations of motion.”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt, further in view of Lin to use a physics-based ROM configured to apply one or more physics-based equations due to their lower computational cost, easy scalability and effectiveness in monitoring the physics of wear. [Lin: Abstract]: “This paper developed a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure, having a lower computational cost and therefore more easily scalable.” [p.2]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others.”
Regarding claim 8, Zhang teaches the computer-implemented method of claim 7, further comprising: …receiving, by the at least one processor, …machine data generated by the track-type machine; …receiving, by the at least one processor, …environmental data associated with the track-type machine; …generating, by the at least one processor, the …estimated wear level of the at least one undercarriage component; [0008]: “A machine includes one or more memories; and one or more processors configured to: receive, from one or more sensor devices of the machine, sensor data associated with wear of one or more components of an undercarriage of the machine; predict, using a machine learning model and the sensor data, an amount wear of the one or more components based on a wear rate of the one or more components, wherein the machine learning model is trained, using training data, to predict the wear rate of the one or more components, wherein the training data includes two or more of: historical sensor data, historical inspection data, or simulation data, of a simulation model, from one or more third devices, and wherein the two or more of the historical sensor data, the historical inspection data, or the simulation data are associated with wear of the one or more components; and perform an action based on the amount of wear of the one or more components.” [0043]: “The historical inspection data may include…environmental conditions at a location associated with machine”, and …comparing, by the at least one processor, the …estimated wear level of the at least one undercarriage component to the wear level threshold; [0030]: “Additionally, or alternatively, sensor system 120 may provide the historical sensor data to wear detection device 190 (e.g., to train machine learning model 230) based on a triggering event (e.g., a request from wear detection device 190, a request from controller 140, and/or a request from an operator of machine 105 (e.g., via the integrated display and/or operator controls)…where [0040] the “controller may include one or more processors…capable of being programmed to perform a function.” [0072]: “Wear detection device 190 may transmit the remaining life information…[0070]: when the amount of wear (of the one or more components) satisfies a threshold amount of wear…”
However, Zhang fails to teach using recursiveness in updating…data.
Niedfeldt teaches a model to recursively update state estimates using sequential measurements [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to use recursiveness in updating…data to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Regarding claim 9, Zhang teaches the computer-implemented method of claim 8, wherein the…estimated wear level is…generated and compared to the wear level threshold on a regular interval of time; [0008]: “A machine includes one or more memories; and one or more processors configured to: receive, from one or more sensor devices of the machine, sensor data associated with wear of one or more components of an undercarriage of the machine; predict, using a machine learning model and the sensor data, an amount wear of the one or more components based on a wear rate of the one or more components, wherein the machine learning model is trained, using training data, to predict the wear rate of the one or more components…” [0072]: “Wear detection device 190 may transmit the remaining life information…[0070]: when the amount of wear (of the one or more components) satisfies a threshold amount of wear…”
However, Zhang fails to teach using recursiveness in updating…data.
Niedfeldt teaches a model to recursively update state estimates using sequential measurements [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to use recursiveness in updating…data to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Regarding claim 10, Zhang teaches the computer-implemented method of claim 7, wherein: comparing the…estimated wear level of the at least one undercarriage component to the wear level threshold further comprises comparing the…estimated wear level to a near-failure threshold; [0070]: “wear detection device 190 may transmit the remaining life information when the amount of wear (of the one or more components) satisfies a threshold amount of wear. The remaining life information may indicate the amount of wear of the one or more components, indicate a wear rate of the one or more components, indicate the remaining life of the one or more components, and/or an offer associated with repairing and/or replacing the one or more components,” and [0076]: “wear detection device 190 may determine whether a failure of the one or more components is imminent (e.g., based on the predicted component wear information). If wear detection device 190 determines that the failure is imminent, wear detection device 190 may perform one or more of the actions described above. If wear detection device 190 determines that the failure is not imminent, wear detection device 190 may not perform an action”, and the at least one processor is further configured to, in response to determining that the …estimated wear level of the at least one undercarriage component exceeds the near-failure threshold, generate an estimate of when the undercarriage component will need to be replaced and cause the control interface to output the estimate; [Claim 12] “…the one or more processors are further configured to: cause an operation of the machine to be adjusted based on the amount of wear of the one or more components; transmit remaining life information to a first device to cause the first device to generate, based on the amount of wear of the one or more components, a service request to at least one of repair or replace the one or more components, wherein the remaining life information indicates the amount of wear of the one or more components; or transmit the remaining life information, to a second device associated with an operator of the machine, to cause the operator to adjust the operation of the machine based on the remaining life information or to transmit the service request using the second device associated with the operator.” [0030]: “Additionally, or alternatively, sensor system 120 may provide the historical sensor data to wear detection device 190 (e.g., to train machine learning model 230) based on a triggering event (e.g., a request from wear detection device 190, a request from controller 140, and/or a request from an operator of machine 105 (e.g., via the integrated display and/or operator controls)…where [0040] the “controller may include one or more processors…capable of being programmed to perform a function.”
However, Zhang does not teach updating…data.
Niedfeldt teaches a model to recursively update state estimates using sequential measurements [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to use updated data to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Regarding claim 11, Zhang teaches the computer-implemented method of claim 7, wherein: comparing the…estimated wear level of the at least one undercarriage component to the wear level threshold further comprises comparing the…estimated wear level to a failure threshold; [0070]: “Wear detection device 190 may transmit the remaining life information when the amount of wear (of the one or more components) satisfies a threshold amount of wear. The remaining life information may indicate the amount of wear of the one or more components, indicate a wear rate of the one or more components, indicate the remaining life of the one or more components, and/or an offer associated with repairing and/or replacing the one or more components,” and [0076]: “wear detection device 190 may determine whether a failure of the one or more components is imminent (e.g., based on the predicted component wear information). If wear detection device 190 determines that the failure is imminent, wear detection device 190 may perform one or more of the actions described above. If wear detection device 190 determines that the failure is not imminent, wear detection device 190 may not perform an action”, and the at least one processor is further configured to, in response to determining that the…estimated wear level of the at least one undercarriage component exceeds the failure threshold, cause the control interface to output an indication that the at least one undercarriage component needs to be replaced; [Claim 12]: “…the one or more processors are further configured to: cause an operation of the machine to be adjusted based on the amount of wear of the one or more components; transmit remaining life information to a first device to cause the first device to generate, based on the amount of wear of the one or more components, a service request to at least one of repair or replace the one or more components, wherein the remaining life information indicates the amount of wear of the one or more components; or transmit the remaining life information, to a second device associated with an operator of the machine, to cause the operator to adjust the operation of the machine based on the remaining life information or to transmit the service request using the second device associated with the operator.”
[0030]: “Additionally, or alternatively, sensor system 120 may provide the historical sensor data to wear detection device 190 (e.g., to train machine learning model 230) based on a triggering event (e.g., a request from wear detection device 190, a request from controller 140, and/or a request from an operator of machine 105 (e.g., via the integrated display and/or operator controls)…where [0040] the “controller may include one or more processors…capable of being programmed to perform a function.”
However, Zhang does not teach updating…data.
Niedfeldt teaches a model to recursively update state estimates using sequential measurements [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to use updated data to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Regarding claim 12, the computer-implemented method of claim 7, further comprising: receiving, by the at least one processor, sensor data that is indirectly indicative of wear of the at least one undercarriage component; [0051]: “Wear detection device 190 (e.g., using machine learning model 230) may identify factors impacting a wear rate of the one or more components (and/or an amount wear of the one or more components). The factors may include the measure of abrasion, the location, the measure of moisture, the operator behavior (which may identify a task performed by machine 105), the distance traveled, the speed associated with the distance traveled, the track tension, the drawbar force, the measure of vibration of machine 105, and/or the measure of sound of machine 105.” [0032]: “The sensor devices may include a vibration sensor device, a sound sensor device, a track link wear sensor device, a location sensor device, a speed sensor device, a motion sensor device, a load sensor device, a pressure sensor device, a flow sensor device, and/or a temperature sensor device.” [0040-0041]: “Controller 140…which may include one or more processors 240…may obtain sensor data (e.g., from sensor system 120) and may cause wear detection device 190 to predict (e.g., using machine learning model 230) an amount of wear of the one or more components based on the sensor data”, and optimizing, by the at least one processor, the…estimated wear level of the at least one undercarriage component by…model…with the sensor data using an adaptive fusion method; [0061]: “When training machine learning model 230, wear detection device 190 may portion the training data into a training set (e.g., a set of data to train machine learning model 230), a validation set (e.g., a set of data used to evaluate a fit of machine learning model 230 and/or to fine tune machine learning model 230), a test set (e.g., a set of data used to evaluate a final fit of machine learning model 230), and/or the like. Wear detection device 190 may preprocess and/or perform dimensionality reduction to reduce the training data to a minimum feature set. Wear detection device 190 may train machine learning model 230 on this minimum feature set, thereby reducing processing to train machine learning model 230, and may apply a classification technique, to the minimum feature set.”
However, Zhang does not teach updating…data and/or a model. Zhang also does not teach the physics-based ROM.
Niedfeldt teaches a model to recursively update state estimates using sequential measurements [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data and/or a model as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to update data and/or a model to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Lin teaches the physics-based reduced order model through the modeling of [Lin: Abstract]: “aero-hydro-servo-elastic (AHSE) dynamics of each wind turbine… where a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure” is used. [p.2]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others.” [p.2]: “All the above ROMs focus on the reduction of the system’s mass and stiffness matrix, derived from the linearization of the system equations of motion.”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt, further in view of Lin to use the physics-based ROM due to their lower computational cost, easy scalability and effectiveness in monitoring the physics of wear. [Lin: Abstract]: “This paper developed a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure, having a lower computational cost and therefore more easily scalable.” [p.2]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others…All the above ROMs focus on the reduction of the system’s mass and stiffness matrix, derived from the linearization of the system equations of motion.”
Regarding claim 13, Zhang teaches the computer-implemented method of claim 7, wherein the at least one processor is further configured to cause the control interface to display the warning notification within an interface built into the track-type machine; [Claim 12]: “…the one or more processors are further configured to: cause an operation of the machine to be adjusted based on the amount of wear of the one or more components; transmit remaining life information to a first device to cause the first device to generate, based on the amount of wear of the one or more components, a service request to at least one of repair or replace the one or more components, wherein the remaining life information indicates the amount of wear of the one or more components; or transmit the remaining life information, to a second device associated with an operator of the machine, to cause the operator to adjust the operation of the machine based on the remaining life information or to transmit the service request using the second device associated with the operator.” [0030]: “Additionally, or alternatively, sensor system 120 may provide the historical sensor data to wear detection device 190 (e.g., to train machine learning model 230) based on a triggering event (e.g., a request from wear detection device 190, a request from controller 140, and/or a request from an operator of machine 105 (e.g., via the integrated display and/or operator controls)…where [0040] the “controller may include one or more processors…capable of being programmed to perform a function.” [0072]: “Wear detection device 190 may transmit the remaining life information…[0070]: when the amount of wear (of the one or more components) satisfies a threshold amount of wear…[0072]: to cause the one or more devices (e.g., controller 140) to cause machine 105 to… cause an alarm to be activated. The alarm may indicate that the one or more components are to be repaired or replaced.”
Regarding claim 14, Zhang teaches a computer-implemented method for monitoring an undercarriage of a track-type machine, the method comprising: [0041]: “Memory 250 includes a random-access memory (RAM), a read only memory (ROM), and/or another type of dynamic or static storage device…that stores information and/or instructions for use by a processor 240 to perform a function.” [0042]: “Wear detection device 190 may include one or more devices (e.g., a server device or a group of server devices) configured to train machine learning model 230 to predict the amount of wear of the one or more components of the undercarriage…and may be implemented by one or more computing resources of a cloud computing environment”, accessing, by at least one processor, a…model corresponding to the track-type machine; receiving, by the at least one processor, an estimated wear level of at least one undercarriage component of a track-type machine; receiving, by the at least one processor, machine signal data generated by the track-type machine; generating, by the at least one processor, an…estimated wear level of the at least one undercarriage component by submitting the estimated wear level of the at least one undercarriage component and the machine signal data generated by the track-type machine to the…model; [0086]: “As further shown in FIG. 3, process 300 may include predicting, using the machine learning model and based on the sensor data, the remaining life of the one or more components (block 350). For example, the first device may predict, using the machine learning model and based on the sensor data, the remaining life of the one or more components.” [0008]: “A machine includes one or more memories; and one or more processors configured to: receive, from one or more sensor devices of the machine, sensor data associated with wear of one or more components of an undercarriage of the machine; predict, using a machine learning model and the sensor data, an amount wear of the one or more components based on a wear rate of the one or more components, wherein the machine learning model is trained, using training data, to predict the wear rate of the one or more components, wherein the training data includes two or more of: historical sensor data, historical inspection data, or simulation data, of a simulation model, from one or more third devices, and wherein the two or more of the historical sensor data, the historical inspection data, or the simulation data are associated with wear of the one or more components; and perform an action based on the amount of wear of the one or more components”, and comparing, by the at least one processor, the…estimated wear level of the at least one undercarriage component to a wear level threshold, wherein the at least one processor is configured to, in response to determining that the…estimated wear level of the at least one undercarriage component exceeds the wear level threshold, causing a control interface associated with the track-type machine to output a warning notification; [0030]: “Additionally, or alternatively, sensor system 120 may provide the historical sensor data to wear detection device 190 (e.g., to train machine learning model 230) based on a triggering event (e.g., a request from wear detection device 190, a request from controller 140, and/or a request from an operator of machine 105 (e.g., via the integrated display and/or operator controls)…where [0040] the “controller may include one or more processors…capable of being programmed to perform a function.” [0072]: “Wear detection device 190 may transmit the remaining life information…[0070]: when the amount of wear (of the one or more components) satisfies a threshold amount of wear…[0072]: to cause the one or more devices (e.g., controller 140) to cause machine 105 to… cause an alarm to be activated. The alarm may indicate that the one or more components are to be repaired or replaced.”
Zhang does not teach updating…data, and Zhang does not teach the reduced order model (ROM).
Niedfeldt teaches a model to recursively update state estimates using sequential measurements [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to use updated data to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Lin teaches the reduced order model through the modeling of [Lin: Abstract]: “aero-hydro-servo-elastic (AHSE) dynamics of each wind turbine… where a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure” is used. [p.2, para. 2, lines 15-17]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others.”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldy, further in view of Lin to use a reduced order model (ROM) because the ROM has a lower computational cost and it is more easily scalable. [Lin: Abstract]: “This paper developed a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure, having a lower computational cost and therefore more easily scalable.” [p.2]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others.”
Regarding claim 15, Zhang teaches the computer-implemented method of claim 14, further comprising: …receiving, by the at least one processor, …machine data generated by the track-type machine; …generating, by the at least one processor, and …estimated wear levels of the at least one undercarriage component; [0008]: “A machine includes one or more memories; and one or more processors configured to: receive, from one or more sensor devices of the machine, sensor data associated with wear of one or more components of an undercarriage of the machine; predict, using a machine learning model and the sensor data, an amount wear of the one or more components based on a wear rate of the one or more components, wherein the machine learning model is trained, using training data, to predict the wear rate of the one or more components, wherein the training data includes two or more of: historical sensor data, historical inspection data, or simulation data, of a simulation model, from one or more third devices, and wherein the two or more of the historical sensor data, the historical inspection data, or the simulation data are associated with wear of the one or more components; and perform an action based on the amount of wear of the one or more components.” [0043]: “The historical inspection data may include…environmental conditions at a location associated with machine”, and …comparing, by the at least one processor, the …estimated wear level of the at least one undercarriage component to the wear level threshold; [0030]: “Additionally, or alternatively, sensor system 120 may provide the historical sensor data to wear detection device 190 (e.g., to train machine learning model 230) based on a triggering event (e.g., a request from wear detection device 190, a request from controller 140, and/or a request from an operator of machine 105 (e.g., via the integrated display and/or operator controls)…where [0040] the “controller may include one or more processors…capable of being programmed to perform a function.” [0072]: “Wear detection device 190 may transmit the remaining life information…[0070]: when the amount of wear (of the one or more components) satisfies a threshold amount of wear…”
However, Zhang fails to teach using recursiveness in updating…data.
Niedfeldt teaches a model to recursively update state estimates using sequential measurements [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to use recursiveness in updating…data to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Regarding claim 16, Zhang teaches the computer-implemented method of claim 15, wherein the…estimated wear level is…generated and compared to the wear level threshold on a regular interval of time; [0008]: “A machine includes one or more memories; and one or more processors configured to: receive, from one or more sensor devices of the machine, sensor data associated with wear of one or more components of an undercarriage of the machine; predict, using a machine learning model and the sensor data, an amount wear of the one or more components based on a wear rate of the one or more components, wherein the machine learning model is trained, using training data, to predict the wear rate of the one or more components…” [0072]: “Wear detection device 190 may transmit the remaining life information…[0070]: when the amount of wear (of the one or more components) satisfies a threshold amount of wear…”
However, Zhang fails to teach using recursiveness in updating…data.
Niedfeldt teaches a model to recursively update state estimates using sequential measurements [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to use recursiveness in updating…data to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Regarding claim 17, Zhang teaches the computer-implemented method of claim 14, wherein accessing the…model corresponding to the track-type machine further comprises accessing a…model configured to…simulate one or more aspects of the track-type machine; [0086]: “As further shown in FIG. 3, process 300 may include predicting, using the machine learning model and based on the sensor data, the remaining life of the one or more components (block 350). For example, the first device may predict, using the machine learning model and based on the sensor data, the remaining life of the one or more components” [0008] “wherein the machine learning model is trained using… simulation data, of a simulation model… associated with wear of the one or more components.”
However, Zhang does not teach the ROM and the physics-based ROM configured to apply one or more physics-based equations.
Lin teaches the physics-based reduced order model configured to apply one or more physics-based equations through the modeling of [Lin: Abstract]: “aero-hydro-servo-elastic (AHSE) dynamics of each wind turbine… where a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure” is used. [p.2]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others.” [p.2]: “All the above ROMs focus on the reduction of the system’s mass and stiffness matrix, derived from the linearization of the system equations of motion.”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use a physics-based ROM configured to apply one or more physics-based equations due to their lower computational cost, easy scalability and effectiveness in monitoring the physics of wear. [Lin: Abstract]: “This paper developed a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure, having a lower computational cost and therefore more easily scalable.” [p.2]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others…All the above ROMs focus on the reduction of the system’s mass and stiffness matrix, derived from the linearization of the system equations of motion.”
Regarding claim 18, Zhang teaches the computer-implemented method of claim 14: further comprising receiving, by the at least one processor, environmental data associated with the track-type machine; and wherein generating the…estimated wear level of the at least one undercarriage component further comprises submitting the estimated wear level of the at least one undercarriage component, the machine signal data generated by the track-type machine, and the environmental data associated with the track-type machine to the…model; [0043]: “The historical inspection data may include…environmental conditions at a location associated with machine.” [0008]: “A machine includes one or more memories; and one or more processors configured to: receive, from one or more sensor devices of the machine, sensor data associated with wear of one or more components of an undercarriage of the machine; predict, using a machine learning model and the sensor data, an amount wear of the one or more components based on a wear rate of the one or more components, wherein the machine learning model is trained, using training data, to predict the wear rate of the one or more components, wherein the training data includes two or more of: historical sensor data, historical inspection data, or simulation data, of a simulation model, from one or more third devices, and wherein the two or more of the historical sensor data, the historical inspection data, or the simulation data are associated with wear of the one or more components; and perform an action based on the amount of wear of the one or more components.” [Claim 12] “…the one or more processors are further configured to: cause an operation of the machine to be adjusted based on the amount of wear of the one or more components; transmit remaining life information to a first device to cause the first device to generate, based on the amount of wear of the one or more components, a service request to at least one of repair or replace the one or more components, wherein the remaining life information indicates the amount of wear of the one or more components; or transmit the remaining life information, to a second device associated with an operator of the machine, to cause the operator to adjust the operation of the machine based on the remaining life information or to transmit the service request using the second device associated with the operator.”
However, Zhang does not teach updating…data and does not teach the ROM.
Niedfeldt teaches a model to recursively update state estimates using sequential measurements [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to use updated data to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Lin teaches the reduced order model through the modeling of [Lin: Abstract]: “aero-hydro-servo-elastic (AHSE) dynamics of each wind turbine… where a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure” is used. [p.2, para. 2, lines 15-17]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others.”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt, further in view of Lin to use a reduced order model (ROM) because the ROM has a lower computational cost and it is more easily scalable. [Lin: Abstract]: “This paper developed a reduced-order model (ROM), able to capture the relevant dynamics of the system for a specific failure, having a lower computational cost and therefore more easily scalable.” [p.2]: “Reduced-order models (ROMs) are well established and widely applied in a variety of areas [10], including static reduction [11], dynamic reduction [12], balanced methods [13], and others.”
Regarding claim 19, Zhang teaches the computer-implemented method of claim 14, wherein: comparing the…estimated wear level of the at least one undercarriage component to the wear level threshold further comprises comparing the…estimated wear level to a near-failure threshold; [0070]: “wear detection device 190 may transmit the remaining life information when the amount of wear (of the one or more components) satisfies a threshold amount of wear. The remaining life information may indicate the amount of wear of the one or more components, indicate a wear rate of the one or more components, indicate the remaining life of the one or more components, and/or an offer associated with repairing and/or replacing the one or more components,” and [0076]: “wear detection device 190 may determine whether a failure of the one or more components is imminent (e.g., based on the predicted component wear information). If wear detection device 190 determines that the failure is imminent, wear detection device 190 may perform one or more of the actions described above. If wear detection device 190 determines that the failure is not imminent, wear detection device 190 may not perform an action”, and the at least one processor is further configured to, in response determining that the… estimated wear level of the at least one undercarriage component exceeds the near-failure threshold, generate an estimate of when the at least one undercarriage component will need to be replaced and causing the control interface to output the estimate; [Claim 12] “…the one or more processors are further configured to: cause an operation of the machine to be adjusted based on the amount of wear of the one or more components; transmit remaining life information to a first device to cause the first device to generate, based on the amount of wear of the one or more components, a service request to at least one of repair or replace the one or more components, wherein the remaining life information indicates the amount of wear of the one or more components; or transmit the remaining life information, to a second device associated with an operator of the machine, to cause the operator to adjust the operation of the machine based on the remaining life information or to transmit the service request using the second device associated with the operator.” [0030]: “Additionally, or alternatively, sensor system 120 may provide the historical sensor data to wear detection device 190 (e.g., to train machine learning model 230) based on a triggering event (e.g., a request from wear detection device 190, a request from controller 140, and/or a request from an operator of machine 105 (e.g., via the integrated display and/or operator controls)…where [0040] the “controller may include one or more processors…capable of being programmed to perform a function.”
However, Zhang does not teach updating…data.
Niedfeldt teaches a model to recursively update state estimates using sequential measurements [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to use updated data to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Regarding claim 20, Zhang teaches the computer-implemented method of claim 14, wherein: comparing the…estimated wear level of the at least one undercarriage component to the wear level threshold further comprises comparing the…estimated wear level to a failure threshold; [0070]: “Wear detection device 190 may transmit the remaining life information when the amount of wear (of the one or more components) satisfies a threshold amount of wear. The remaining life information may indicate the amount of wear of the one or more components, indicate a wear rate of the one or more components, indicate the remaining life of the one or more components, and/or an offer associated with repairing and/or replacing the one or more components,” and [0076]: “wear detection device 190 may determine whether a failure of the one or more components is imminent (e.g., based on the predicted component wear information). If wear detection device 190 determines that the failure is imminent, wear detection device 190 may perform one or more of the actions described above. If wear detection device 190 determines that the failure is not imminent, wear detection device 190 may not perform an action”, and the at least one processor is further configured to, in response to determining that the…estimated wear level of the at least one undercarriage component exceeds the failure threshold, cause the control interface to output an indication that the undercarriage component needs to be replaced; [Claim 12]: “…the one or more processors are further configured to: cause an operation of the machine to be adjusted based on the amount of wear of the one or more components; transmit remaining life information to a first device to cause the first device to generate, based on the amount of wear of the one or more components, a service request to at least one of repair or replace the one or more components, wherein the remaining life information indicates the amount of wear of the one or more components; or transmit the remaining life information, to a second device associated with an operator of the machine, to cause the operator to adjust the operation of the machine based on the remaining life information or to transmit the service request using the second device associated with the operator.”
[0030]: “Additionally, or alternatively, sensor system 120 may provide the historical sensor data to wear detection device 190 (e.g., to train machine learning model 230) based on a triggering event (e.g., a request from wear detection device 190, a request from controller 140, and/or a request from an operator of machine 105 (e.g., via the integrated display and/or operator controls)…where [0040] the “controller may include one or more processors…capable of being programmed to perform a function.”
However, Zhang does not teach updating…data.
Niedfeldt teaches a model to recursively update state estimates using sequential measurements [p.464-465]: “The recently developed R-RANSAC algorithm described in this paper extends the traditional RANSAC algorithm to recursively update state estimates using sequential measurements…where for each new measurement scan, R-RANSAC tests each measurement to see if it is an inlier to one or more existing tracks. If so, those tracks are updated”, and [p.462]: “The R-RANSAC algorithm...robustly and recursively tracks multiple targets in clutter…and stores a set of validated hypotheses, or tracks, between time steps and uses subsequent measurements to either update existing tracks or seed new tracks…and it was first developed to estimate parameters of signals.”
The need for updating is pointed out by Zhang [0002-0003] as “…obtaining manual measurements requires the machine to suspend performing the task and is a time consuming process (e.g., due to the travel time for obtaining manual measurements and/or the amount of time for obtaining manual measurements), obtaining manual measurements may negatively affect productivity at the work site. In this regard, the task (that is to be performed by the machine) may be suspended for a long period of time (e.g., a period of time during which the manual measurements are obtained). Additionally, such manual measurements can be inaccurate. Inaccurate measurements of component dimensions, in turn, may result in incorrect predictions regarding a remaining life of the components. As a result of such incorrect predictions, the components may either fail prematurely or may be repaired or replaced prematurely (e.g., because the components may not be sufficiently worn to require replacement or repair). Such premature failure of the components or premature replacement or repair of the components also negatively affects productivity at the work site. Accordingly, the above technique for detecting wear of the components need to be improved to prevent or reduce down time at the work site (e.g., down time associated with obtaining manual measurements of component dimensions, associated with premature failure of components, associated with premature repair of components, associated with premature replacement of components, and/or the like).”
The benefit of updating is pointed out by [Niedfeldt: Abstract]: “R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.” [p.464-465] Recursively updating state estimates using sequential measurements helps to avoid recomputing hypotheses between time steps…and allows for modular incorporation of various data association, state update, and other techniques.”
The combination of Zhang and Niedfeldt describe the need and benefits of using a recursive method to update data as a necessity in a dynamic monitoring system for real-time state updates used for accurate and timely wear detection given that wear is cumulative, and without updated data, timely repairs and replacements of undercarriage components in a track-type machine would be significantly more time consuming.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang in view of Niedfeldt to use updated data to have lower computational complexity and avoid recomputing hypotheses and have more accurate measurements of state over time.
Conclusion
An inquiry concerning this communication or earlier communication from the examiner should be directed to LOGAN D COONS whose telephone number is
(571) 272-2698. (via email: logan.coons@uspto.gov “without a written authorization by applicant in place, the USPTO will not respond via internet e-mail to an internet correspondence” MPEP 502.02 II). The examiner can normally be reached on M-F 9:30am – 6pm ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, SPE Alexander Satanovsky, can be reached at (571) 270-5819. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/LOGAN D COONS/Examiner, Art Unit 2857
/ALEXANDER SATANOVSKY/Primary Examiner, Art Unit 2863