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
Response to Arguments
Applicant’s arguments, see applicant’s remarks pages 7-10, filed 12/03/2025, with respect to the rejection(s) of claim(s) 1, 3-4, 6, 8-10 under 35 USC 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Kretschmann, et al. (U.S. Patent Application Pub. No. 2020/0189328).
Applicant's arguments filed 12/03/2025, in regards to claims 11 and 21, and their dependent claims, have been fully considered but they are not persuasive. In regards to claims 11 and 21, the applicant argues that the prior art of record does not teach the limitations “inspection data” and “operational data” (See detailed arguments in applicant’s remarks pages 7-8). In regards to the “inspection data”, the current pending claims teach “wherein the historical inspection data comprises one or more of a link height, a bushing wear, a grouser wear, and a track extension”. Zhang teaches “historical inspection data” which includes “a measure of wear of the one or more components, an overall assessment of a condition of the one or more components”, etc., where the components listed in Zhang include “one or more track link bushings” (Zhang, Para. 0024 and 0043), such that Zhang teaches inspection data relating to bushing wear, as listed as one of many options in the claims.
In regards to “operational data” comprising “one or more of a forward distance traveled by a track of the tracked undercarriage, a reverse distance traveled by the track of the tracked undercarriage, a duration of operation by the tracked undercarriage, and a rotational torque associated with the track of the tracked undercarriage”, as taught in the current pending claims, the previous office action, dated 09/03/2025, relies on the combination of Zhang and Mhadbi, to teach the limitations, rather than Zhang taken alone, as argued. Mhadbi teaches a duration of operation by the tracked undercarriage (Mhadbi, Para. 0016-0023 and 0026 – where data used to train a “statistical model” include “service hours” and other objects used to derive “total travel time”, “travel hours per steering”, “travel hours per slope”, etc.; where the statistical model is used to predict wear of undercarriage components such as a track chain, a track roller, etc.), and a rotational torque associated with the track of the tracked undercarriage (Mhadbi, Para. 0016, 0019 and 0026 – where derived data of the components of the undercarriage used to train the statistical model includes “drive torque”).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
Claim(s) 1, 3-4, and 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang, et al., hereinafter Zhang (U.S. Patent Application Pub. No. 2022/0139117) in view of Johannsen (U.S. Patent Application Pub. No. 2023/0110852), and further in view of Mhadbi, et al., hereinafter Mhadbi (U.S. Patent Application Pub. No. 2023/0135656) and Kretschmann, et al., hereinafter Kretschmann (U.S. Patent Application Pub. No. 2020/0189328).
Regarding Claim 1, Zhang teaches: A predictive maintenance system utilized in conjunction with a work machine having a tracked undercarriage (Zhang, Para. 0009, 0013, and 0060 – a “system” which includes a “device” configured to “predict, using a machine learning model and based on the sensor data, a remaining life of the one or more components of an undercarriage of a machine”; where the machine is, for example, “any machine that performs an operation associated with an industry such as, for example, mining, construction, farming, transportation, or another industry”), the predictive maintenance system comprising:
the tracked undercarriage (Zhang, Para. 0009 and 0022-0024 – “an undercarriage of machine” having “ground engaging members” which are “tracks”);
a power source operatively coupled to the tracked undercarriage (Zhang, Para. 0016 and 0022 – an “engine”, or power source, which “provides power to machine 105 and/or a set of loads (e.g., components that absorb power and/or use power to operate) associated with machine”, including the “ground engaging members”, or tracks); and
a controller operatively coupled to the power source (Zhang, Para. 0016 – “engine 110 may provide power to one or more control systems (e.g., controller 140)”, such that they are coupled), the controller comprising one or more processors and a memory having a predictive maintenance algorithm stored thereon (Zhang, Para. 0020 and 0040-0041 – where the “controller” may “include one or more processors” and “one or more memories”, where the processors “may be capable of being programmed to perform a function”; where the memory contains “information and/or instructions for use by a processor” such as predicting “(e.g., using machine learning model 230) an amount of wear of the one or more components based on the sensor data”), wherein the processor is operable to execute the predictive maintenance algorithm to:
receive a historical operational data from sensors associated with the operation of the tracked undercarriage (Zhang, Para. 0048-0049 and 0056 – where a “wear detection device 190”, used for training the “machine learning model”, “may receive the historical sensor data from sensor system 120” to “predict the amount of wear of the one or more components of the undercarriage”; where “historical sensor data” includes “historical load data, historical speed data, historical distance data and/or historical temperature data”),
receive a historical inspection data associated with the amount of wear of the tracked undercarriage (Zhang, Para. 0043-0044 – where an “inspection device” may provide “historical inspection data regarding historical inspections of machine” to the “wear detection device” which is “used to train machine learning model 230”), wherein the historical inspection data comprises one or more of a link height, a bushing wear (Zhang, Para. 0024 and 0043 – where “historical inspection data” includes “a measure of wear of the one or more components, an overall assessment of a condition of the one or more components”, etc., where the components include “one or more track link bushings”), a grouser wear, and a track extension;
extract a one or more features from the historical operational data, the one or more features including at least one operation parameter associated with wear of the tracked undercarriage (Zhang, Para. 0050-0060 – where the machine learning model is trained on “historical sensor data”, where the model may help “identify”, or extract, “factors impacting a wear rate of the one or more components” of the undercarriage, such as “track tension”, location, moisture, etc.);
train a predictive model using the one or more features, the historical inspection data, and a labeled dataset regarding an actual maintenance need or health information of the tracked undercarriage (Zhang, Para. 0043, 0050-0061 – where the machine learning model is trained on “historical sensor data”, where “factors impacting a wear rate” are identified, “historical inspection data”, and “a training set (e.g., a set of data to train machine learning model 230)”, to “predict the wear rate and/or the amount of wear of the one or more components” of the undercarriage having tracks);
apply the predictive model to the one or more features to generate a prediction of the maintenance needs or health information of one or more components of the tracked undercarriage (Zhang, Para. 0028, 0060 and 0070 – where the machine learning model is used to “predict the wear rate and/or the amount of wear of the one or more components” of the undercarriage and to determine and transmit “remaining life information when the amount of wear (of the one or more components) satisfies a threshold amount of wear”; where the undercarriage components include one or more tracks, track links, etc.); and
outputting a where the “wear detection device” may “transmit the remaining life information to cause the one or more devices (e.g., controller 140) to cause an alarm to be activated”, where the alarm indicates “that the one or more components are to be repaired or replaced”)
While Zhang teaches output an indication of the prediction or health information to an operator interface, Zhang does not specifically teach outputting a visual indication of the prediction or health information. Additionally, while Zhang teaches historical operation data, Zhang does not teach wherein the historical operation comprises one or more of a forward distance traveled by a track of the tracked undercarriage, a reverse distance traveled by the track of the tracked undercarriage, a duration of operation by the tracked undercarriage, and a rotational torque associated with the track of the tracked undercarriage, and wherein extraction of features from the historical operation data initiate after a break-in threshold of operation duration or a traveled distance.
However, Johannsen teaches outputting a visual indication of the prediction or health information (Johannsen, Para. 0037 – where an “on-board computer” may “display wear information (e.g., to an operator of the machine 10)”, such as “safety messages regarding the state of the track assembly 14, an estimated operating time until service will be necessary, etc.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the predictive maintenance system of Zhang to include outputting a visual indication of the prediction or health information, as taught by Johannsen, in order to present the indication of the prediction of health information to the operator through a visual means as a method to alert the operator of a need for inspection or repair.
While Zhang teaches historical operational data from sensors associated with the operation of the tracked undercarriage, Zhang in view of Johannsen does not teach wherein the historical operation comprises one or more of a forward distance traveled by a track of the tracked undercarriage, a reverse distance traveled by the track of the tracked undercarriage, a duration of operation by the tracked undercarriage, and a rotational torque associated with the track of the tracked undercarriage, and wherein extraction of features from the historical operation data initiate after a break-in threshold of operation duration or a traveled distance.
However, Mhadbi teaches wherein the historical operation comprises one or more of a forward distance traveled by a track of the tracked undercarriage, a reverse distance traveled by the track of the tracked undercarriage, a duration of operation by the tracked undercarriage (Mhadbi, Para. 0016-0023 and 0026 – where data used to train a “statistical model” include “service hours” and other objects used to derive “total travel time”, “travel hours per steering”, “travel hours per slope”, etc.; where the statistical model is used to predict wear of undercarriage components such as a track chain, a track roller, etc.), and a rotational torque associated with the track of the tracked undercarriage (Mhadbi, Para. 0016, 0019 and 0026 – where derived data of the components of the undercarriage used to train the statistical model includes “drive torque”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the predictive maintenance system including the above limitations of Zhang in view of Johannsen to include wherein the wherein the historical operation comprises one or more of a duration of operation by the tracked undercarriage; and a rotational torque associated with the track of the tracked undercarriage, as taught by Mhadbi, in order to determine historical operations and their impact on the wear of the tracked undercarriage to improve accuracy of the predictions of the model.
Zhang in view of Johannsen and Mhadbi does not teach wherein extraction of features from the historical operation data initiate after a break-in threshold of operation duration or a traveled distance.
However, Kretschmann teaches wherein extraction of features from the historical operation data initiate after a break-in threshold of operation duration or a traveled distance (Kretschmann, Para. 0015-0020, 0050, 0064-0069, and 0124 – a model for determining tire tread depth, or wear, where determination of the tread depth is performed when the tire has reached “a predetermined minimum mileage”, for example “the predetermined minimum mileage to be at least 50 km, in particular at least 100 km”, wherein the model is built using “adaptation data transmitted from” a “plurality of vehicles”, or historical data, on the basis of mileage of the tire; where it is known in the art that a tired is part of a vehicle undercarriage).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the predictive maintenance system including the above limitations of Zhang in view of Johannsen and Mhadbi to include wherein extraction of features from the historical operation data initiate after a traveled distance, as taught by Kretschmann, in order to improve the accuracy of the predictive maintenance system for the undercarriage.
In regards to Claim 3, Zhang in view of Johannsen, Mhadbi, and Kretschmann teaches the predictive maintenance system of Claim 1, and Zhang teaches the feature from the historical operational data (Zhang, Para. 0050-0060 – where the machine learning model is trained on “historical sensor data”, where the model may help “identify”, or extract, “factors impacting a wear rate of the one or more components” of the undercarriage, such as “track tension”, etc.), but Zhang does not specifically teach wherein the features are derived from each a left and right track of the tracked undercarriage.
However, Johannsen teaches wherein the features are derived from each a left and right track of the tracked undercarriage (Johannsen, Para. 0002, 0018, 0029, and 0040 – a machine having a “tracked undercarriage” including “a pair of track assemblies” on “the left and right sides of the machine”; where a “monitoring system” may track a feature, in this case “track wrap angle”, of the track assemblies “over a period of time”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the predictive maintenance system including the above limitations of Zhang in view of Johannsen, Mhadbi, and Kretschmann to further include wherein the features are derived from each a left and right track of the tracked undercarriage, as taught by Johannsen, in order to determine the wear of both the left and right tracks of a tracked undercarriage to perform maintenance on both tracks.
In regards to Claim 4, Zhang in view of Johannsen, Mhadbi, and Kretschmann teaches the predictive maintenance system of Claim 1, and Zhang teaches the feature from the historical operational data (Zhang, Para. 0050-0060 – where the machine learning model is trained on “historical sensor data”, where the model may help “identify”, or extract, “factors impacting a wear rate of the one or more components” of the undercarriage, such as “track tension”, etc.) comprises a power source utilization (Zhang, Para. 0037 – “sensing a load of engine 110 and generate load data identifying a load of engine”), but Zhang does not teach a power source utilization duration with a low load condition, a medium load condition, and a high load condition.
However, Mhadbi teaches a power source utilization duration with a low load condition, a medium load condition, and a high load condition (Mhadbi, Para. 0022 – a “travel hours per load” having sub-features “such as “heavy” “moderate” and “light”” conditions, where the engine powers the machine for travel).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the predictive maintenance system including the above limitations of Zhang in view of Johannsen, Mhadbi, and Kretschmann to further include a power source utilization duration with a low load condition, a medium load condition, and a high load condition, as taught by Mhadbi, in order to include data on low condition in the predictive maintenance system to assess how load affects wear and improve accuracy of the predictions.
In regards to Claim 9, Zhang in view of Johannsen, Mhadbi, and Kretschmann teaches the predictive maintenance system of Claim 1, and Zhang further teaches wherein the predictive model is periodically applied (Zhang, Para. 0030-0031 and 0063-0066 – where the machine learning model “may be retrained on a periodic basis” with periodically provided data), updating the prediction and health information outputs to one of a plurality of communicatively coupled work machines, a central operating center (Zhang, Para. 0063-0070 – where the periodically retrained machine learning model determines “predicted amount of wear of the one or more components” and where the “wear detection device” can transmit “remaining life information to one or more devices that monitor an amount of wear of components of a plurality of machines”, where “one or more devices” includes “a device of the site management system”), and a dealers.
In regards to Claim 10, Zhang in view of Johannsen, Mhadbi, and Kretschmann teaches the predictive maintenance system of Claim 1, and Zhang further teaches wherein the features from the historical operational data comprises a power source utilization for a sprocket movement (Zhang, Para. 0016, 0023, and 0056 – wherein the “wear detection device” determines that “wear rate of the one or more components increases as the load of engine” increases, where this is determined using “historical load data” when performing a task; where to perform a task, the engine provides power to the machine and “set of loads (e.g., components that absorb power and/or use power to operate) associated with machine”, including “ground engaging members”, where the ground engaging members are driven by a “sprocket”) and an implement movement (Zhang, Para. 0016-0017, 0037 and 0056 – where the engine powers a load and historical load data is used by the wear detection device; where the engine powers “components (e.g., one or more hydraulic pumps, one or more actuators, and/or one or more electric motors) to facilitate control of rear attachment 150 and/or front attachment 160 of machine”, such that the attachments, or implements, contribute to the load of the engine).
Claim(s) 6 is rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Johannsen, Mhadbi, and Kretschmann, and further in view of Jang (U.S. Patent Application Pub. No. 2017/0328031).
In regards to Claim 6, Zhang in view of Johannsen, Mhadbi, and Kretschmann teaches the predictive maintenance system of Claim 1, and Zhang teaches the historical inspection data (Zhang, Para. 0043-0044 – where an “inspection device” may provide “historical inspection data regarding historical inspections of machine” including “times and/or dates associated with when the historical inspections were performed”), but Zhang does not specifically teach wherein the historical inspection data is derived from a last known inspection data.
However, Jang teaches wherein the historical inspection data is derived from a last known inspection data (Jang, Para. 0044 – a controller generates a “machine application profile may be used to predict a potential failure of a component of machine”, where the profile is generated using “records of treatments and maintenance”, for example the controller “may check the last time this component was examined” when an activity that may cause wear is identified).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the predictive maintenance system including the above limitations of Zhang in view of Johannsen, Mhadbi, and Kretschmann to include wherein the historical inspection data is derived from a last known inspection data, as taught by Jang, in order to use the most recent inspection data to prove a predictive maintenance system with the most up-to-date and accurate data.
Claim(s) 8 is rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Johannsen, Mhadbi, and Kretschmann, and further in view of Ricci (U.S. Patent Application Pub. No. 2016/0039426) and Kumar, et al., hereinafter Kumar (U.S. Patent Application Pub. No. 2018/0240290).
In regards to Claim 8, Zhang in view of Johannsen, Mhadbi, and Kretschmann teaches the predictive maintenance system of Claim 1, and Zhang further teaches wherein the historical operational data is derived from an aggregate historical operational data from two or more work machines with at least a similar machine type (Zhang, Para. 0050 – “machine learning model 230 may be trained to predict an amount of wear of one or more components of an undercarriage of a group of machines that are similar to machine” where the machine learning model is uses “training data” which includes “historical sensor data, historical inspection data, and/or simulation data associated with the group of machines”), geographic location, a soil type (Zhang, Para. 0045 – “environmental data identifying environmental conditions at the location during performance of the task”, such as “moisture data identifying a measure of moisture (e.g., moisture of soil) at the location and/or dryness data identifying a measure of dryness (e.g., dryness of soil) at the location”), a work machine operation type (Zhang, Para. 0050 – “similar or same type of tasks performed”).
While Zhang teaches wherein the historical operational data is derived from an aggregate historical operational data from two or more work machines with at least a similar machine type, a geographic location, a soil type, and a work machine operation type, Zhang does not teach an aggregate historical operational data from two or more work machines with at least a similar operator and a dealer.
Ricci teaches an aggregate historical operational data from two or more work machines with at least a similar operator (Ricci, Claim 21 – a storage system storing “tracked user behavior for the user from a plurality of vehicles”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the predictive maintenance system including the above limitations of Zhang in view of Johannsen and Larsson to include an aggregate historical operational data from two or more work machines with at least a similar operator, as taught by Ricci, in order to take into account an operator behavior to improve maintenance predictions, as operator behavior when operating a work machine may impact the amount of wear on the components.
Zhang in view of Johannsen, Mhadbi, Kretschmann, and Ricci does not teach an aggregate historical operational data from two or more work machines with at least a similar dealer.
However, Kumar teaches an aggregate historical operational data from two or more work machines with at least a similar dealer (Kumar, Para. 0041-0042 and 0052-0055 – where a system receives “a repair or malfunction report from a vehicle diagnostic unit and/or a dealer or mechanic maintenance system” from multiple vehicles for analysis; where vehicles are associated with a dealer, and the dealer utilizes the repair/malfunction reports for repairs for the multiple vehicles).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the predictive maintenance system including the above limitations of Zhang in view of Johannsen, Larsson, and Ricci to include an aggregate historical operational data from two or more work machines with at least a similar dealer, as taught by Kumar, in order to group vehicles by the same dealer when performing maintenance predictions to alert the dealer of vehicles in need of maintenance and to improve predictions.
Claim(s) 11, 13-14, 17 and 19-21 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Johannsen and Mhadbi.
Regarding Claim 11, Zhang teaches: A method for performing a predictive maintenance of a tracked undercarriage on a work machine (Zhang, Para. 0007-0009, 0013, and 0060 – a “method” performed by a “device” configured to “predict, using a machine learning model and based on the sensor data, a remaining life of the one or more components of an undercarriage of a machine”; where the machine is, for example, “any machine that performs an operation associated with an industry such as, for example, mining, construction, farming, transportation, or another industry”), comprising:
receiving a historical operational data from sensors associated with the operation of the tracked undercarriage (Zhang, Para. 0048-0049 and 0056 – where a “wear detection device 190”, used for training the “machine learning model”, “may receive the historical sensor data from sensor system 120” to “predict the amount of wear of the one or more components of the undercarriage”; where “historical sensor data” includes “historical load data, historical speed data, historical distance data and/or historical temperature data”),
receiving a historical inspection data associated with an amount of wear of the tracked undercarriage (Zhang, Para. 0043-0044 – where an “inspection device” may provide “historical inspection data regarding historical inspections of machine” to the “wear detection device” which is “used to train machine learning model 230”) wherein the historical inspection data comprises one or more of a link height, a bushing wear (Zhang, Para. 0024 and 0043 – where “historical inspection data” includes “a measure of wear of the one or more components, an overall assessment of a condition of the one or more components”, etc., where the components include “one or more track link bushings”), a grouser wear, and a track extension;
extracting one or more features from the historical operational data , the one or more features including at least one operation parameter associated with wear of the tracked undercarriage (Zhang, Para. 0050-0060 – where the machine learning model is trained on “historical sensor data”, where the model may help “identify”, or extract, “factors impacting a wear rate of the one or more components” of the undercarriage, such as “track tension”, location, moisture, etc.);
training a predictive model using the one or more features, the historical inspection data, and a labeled dataset regarding an actual maintenance need or health information of the tracked undercarriage (Zhang, Para. 0043, 0050-0061 – where the machine learning model is trained on “historical sensor data”, where “factors impacting a wear rate” are identified, “historical inspection data”, and “a training set (e.g., a set of data to train machine learning model 230)”, to “predict the wear rate and/or the amount of wear of the one or more components” of the undercarriage having tracks); and
applying the predictive model to the one or more features to generate a prediction of the maintenance needs or health information of one or more components of the tracked undercarriage (Zhang, Para. 0028, 0060 and 0070 – where the machine learning model is used to “predict the wear rate and/or the amount of wear of the one or more components” of the undercarriage and to determine and transmit “remaining life information when the amount of wear (of the one or more components) satisfies a threshold amount of wear”; where the undercarriage components include one or more tracks, track links, etc.).
While Zhang teaches outputting the prediction or health information to an operator, Zhang does not specifically teach outputting the prediction or health information to an operator interface. Additionally, while Zhang teaches historical operational data, Zhang does not teach wherein the historical operation comprises one or more of a forward distance traveled by a track of the tracked undercarriage, a reverse distance traveled by the track of the tracked undercarriage, a duration of operation by the tracked undercarriage, and a rotational torque associated with the track of the tracked undercarriage.
However, Johannsen teaches outputting the prediction or health information to an operator interface (Johannsen, Para. 0037 – where an “on-board computer” may “display wear information (e.g., to an operator of the machine 10)”, such as “safety messages regarding the state of the track assembly 14, an estimated operating time until service will be necessary, etc.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Zhang to include outputting the prediction or health information to an operator interface, as taught by Johannsen, in order to present the indication of the prediction of health information to the operator through a visual means as a method to alert the operator of a need for inspection or repair.
Zhang in view of Johannsen does not teach wherein the historical operation comprises one or more of a forward distance traveled by a track of the tracked undercarriage, a reverse distance traveled by the track of the tracked undercarriage, a duration of operation by the tracked undercarriage, and a rotational torque associated with the track of the tracked undercarriage.
However, Mhadbi teaches wherein the historical operation comprises one or more of a forward distance traveled by a track of the tracked undercarriage, a reverse distance traveled by the track of the tracked undercarriage, a duration of operation by the tracked undercarriage (Mhadbi, Para. 0016-0023 and 0026 – where data used to train a “statistical model” include “service hours” and other objects used to derive “total travel time”, “travel hours per steering”, “travel hours per slope”, etc.; where the statistical model is used to predict wear of undercarriage components such as a track chain, a track roller, etc.) and a rotational torque of the track of the tracked undercarriage (Mhadbi, Para. 0016, 0019 and 0026 – where derived data of the components of the undercarriage used to train the statistical model includes “drive torque”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the method including the above limitations of Zhang in view of Johannsen to include wherein the feature comprises one or more of: a duration of operation by the tracked undercarriage; and a rotational torque of the track of the tracked undercarriage, as taught by Mhadbi, in order to model various features and determine their impact on the wear of the tracked undercarriage to improve accuracy of the predictions of the model.
In regards to Claim 13, Zhang in view of Johannsen and Mhadbi teaches the method of Claim 12, and Zhang teaches the feature from the historical operational data (Zhang, Para. 0050-0060 – where the machine learning model is trained on “historical sensor data”, where the model may help “identify”, or extract, “factors impacting a wear rate of the one or more components” of the undercarriage, such as “track tension”, etc.), but Zhang does not specifically teach wherein the features are derived from each a left and right track of the tracked undercarriage.
However, Johannsen teaches wherein the features are derived from each a left and right track of the tracked undercarriage (Johannsen, Para. 0002, 0018, 0029, and 0040 – a machine having a “tracked undercarriage” including “a pair of track assemblies” on “the left and right sides of the machine”; where a “monitoring system” may track a feature, in this case “track wrap angle”, of the track assemblies “over a period of time”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method including the above limitations of Zhang in view of Johannsen and Mhadbi to further include wherein the features are derived from each a left and right track of the tracked undercarriage, as taught by Johannsen, in order to determine the wear of both the left and right tracks of a tracked undercarriage to perform maintenance on both tracks.
In regards to Claim 14, Zhang in view of Johannsen and Mhadbi teaches the method of Claim 11, and Zhang teaches the features from the historical operational data (Zhang, Para. 0050-0060 – where the machine learning model is trained on “historical sensor data”, where the model may help “identify”, or extract, “factors impacting a wear rate of the one or more components” of the undercarriage, such as “track tension”, etc.) comprises a power source utilization (Zhang, Para. 0037 – “sensing a load of engine 110 and generate load data identifying a load of engine”), but Zhang does not teach a power source utilization duration with a low load condition, a medium load condition, and a high load condition.
However, Mhadbi teaches a power source utilization duration with a low load condition, a medium load condition, and a high load condition (Mhadbi, Para. 0022 – a “travel hours per load” having sub-features “such as “heavy” “moderate” and “light”” conditions, where the engine powers the machine for travel).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method including the above limitations of Zhang in view of Johannsen and Mhadbi to further include a power source utilization duration with a low load condition, a medium load condition, and a high load condition, as taught by Mhadbi, in order to include data on low condition in the predictive maintenance system to assess how load affects wear and improve accuracy of the predictions.
In regards to Claim 17, Zhang in view of Johannsen and Mhadbi teaches the method of Claim 11, and Zhang further teaches wherein extraction of features from the historical operational data initiate after a threshold of operation duration (Zhang, Para. 0030 – where “sensor system 120 may provide the historical sensor data to wear detection device 190 periodically (e.g., every hour, every other hour, and/or every work shift)”; where the model identifies, or extracts, “factors impacting a wear rate of the one or more components” of the undercarriage from the historical sensor data) or a travelled distance.
In regards to Claim 19, Zhang in view of Johannsen and Mhadbi teaches the method of Claim 11, and Zhang further teaches wherein the predictive model is periodically applied (Zhang, Para. 0030-0031 and 0063-0066 – where the machine learning model “may be retrained on a periodic basis” with periodically provided data), updating the prediction and health information outputs to one of a plurality of communicatively coupled work machines, a central operating center (Zhang, Para. 0063-0070 – where the periodically retrained machine learning model determines “predicted amount of wear of the one or more components” and where the “wear detection device” can transmit “remaining life information to one or more devices that monitor an amount of wear of components of a plurality of machines”, where “one or more devices” includes “a device of the site management system”), and a dealers.
In regards to Claim 20, Zhang in view of Johannsen and Mhadbi teaches the method of Claim 11, and Zhang further teaches wherein the features from the historical operational data comprises a power source utilization for a sprocket movement (Zhang, Para. 0016, 0023, and 0056 – wherein the “wear detection device” determines that “wear rate of the one or more components increases as the load of engine” increases, where this is determined using “historical load data” when performing a task; where to perform a task, the engine provides power to the machine and “set of loads (e.g., components that absorb power and/or use power to operate) associated with machine”, including “ground engaging members”, where the ground engaging members are driven by a “sprocket”) and an implement movement (Zhang, Para. 0016-0017, 0037 and 0056 – where the engine powers a load and historical load data is used by the wear detection device; where the engine powers “components (e.g., one or more hydraulic pumps, one or more actuators, and/or one or more electric motors) to facilitate control of rear attachment 150 and/or front attachment 160 of machine”, such that the attachments, or implements, contribute to the load of the engine).
Regarding Claim 21, Zhang teaches: A predictive maintenance system utilized in conjunction with a work machine having a tracked undercarriage (Zhang, Para. 0009, 0013, and 0060 – a “system” which includes a “device” configured to “predict, using a machine learning model and based on the sensor data, a remaining life of the one or more components of an undercarriage of a machine”; where the machine is, for example, “any machine that performs an operation associated with an industry such as, for example, mining, construction, farming, transportation, or another industry”), the predictive maintenance system comprising:
the tracked undercarriage (Zhang, Para. 0009 and 0022-0024 – “an undercarriage of machine” having “ground engaging members” which are “tracks”);
a power source operatively coupled to the tracked undercarriage (Zhang, Para. 0016 and 0022 – an “engine”, or power source, which “provides power to machine 105 and/or a set of loads (e.g., components that absorb power and/or use power to operate) associated with machine”, including the “ground engaging members”, or tracks); and
a controller operatively coupled to the power source (Zhang, Para. 0016 – “engine 110 may provide power to one or more control systems (e.g., controller 140)”, such that they are coupled), the controller comprising one or more processors and a memory having a predictive maintenance algorithm stored thereon (Zhang, Para. 0020 and 0040-0041 – where the “controller” may “include one or more processors” and “one or more memories”, where the processors “may be capable of being programmed to perform a function”; where the memory contains “information and/or instructions for use by a processor” such as predicting “(e.g., using machine learning model 230) an amount of wear of the one or more components based on the sensor data”), wherein the processor is operable to execute the predictive maintenance algorithm to:
receive a historical operational data from sensors associated with the operation of the tracked undercarriage (Zhang, Para. 0048-0049 and 0056 – where a “wear detection device 190”, used for training the “machine learning model”, “may receive the historical sensor data from sensor system 120” to “predict the amount of wear of the one or more components of the undercarriage”; where “historical sensor data” includes “historical load data, historical speed data, historical distance data and/or historical temperature data”),
receive a historical inspection data associated with the amount of wear of the tracked undercarriage (Zhang, Para. 0043-0044 – where an “inspection device” may provide “historical inspection data regarding historical inspections of machine” to the “wear detection device” which is “used to train machine learning model 230”), wherein the historical inspection data comprises one or more of a link height, a bushing wear (Zhang, Para. 0024 and 0043 – where “historical inspection data” includes “a measure of wear of the one or more components, an overall assessment of a condition of the one or more components”, etc., where the components include “one or more track link bushings”), a grouser wear, and a track extension;
extract a one or more features from the historical operational data, the one or more features including at least one operation parameter associated with wear of the tracked undercarriage (Zhang, Para. 0050-0060 – where the machine learning model is trained on “historical sensor data”, where the model may help “identify”, or extract, “factors impacting a wear rate of the one or more components” of the undercarriage, such as “track tension”, location, moisture, etc.);
train a predictive model using the one or more features, the historical inspection data, and a labeled dataset regarding an actual maintenance need or health information of the tracked undercarriage (Zhang, Para. 0043, 0050-0061 – where the machine learning model is trained on “historical sensor data”, where “factors impacting a wear rate” are identified, “historical inspection data”, and “a training set (e.g., a set of data to train machine learning model 230)”, to “predict the wear rate and/or the amount of wear of the one or more components” of the undercarriage having tracks);
apply the predictive model to the one or more features to generate a prediction of the maintenance needs or health information of one or more components of the tracked undercarriage (Zhang, Para. 0028, 0060 and 0070 – where the machine learning model is used to “predict the wear rate and/or the amount of wear of the one or more components” of the undercarriage and to determine and transmit “remaining life information when the amount of wear (of the one or more components) satisfies a threshold amount of wear”; where the undercarriage components include one or more tracks, track links, etc.); and
outputting a where the “wear detection device” may “transmit the remaining life information to cause the one or more devices (e.g., controller 140) to cause an alarm to be activated”, where the alarm indicates “that the one or more components are to be repaired or replaced”),
wherein the predictive model is periodically applied, updating the prediction and health information outputs to one of a plurality of communicatively coupled work machines (Zhang, Para. 0031 – “After machine learning model 230 has been trained, sensor system 120 may provide the sensor data as an input to machine learning model 230 to predict the amount of wear of the one or more components. Sensor system 120 may provide the sensor data as input to machine learning model 230 on a periodic basis and/or based on a triggering event.”), a central operating center to coordinate a service cycle for a plurality of work machines at worksite through prediction of an estimated product life (Zhang, Para. 0070 and 0072 – “transmitting remaining life information to one or more devices that monitor an amount of wear of components of a plurality of machines (e.g., including machine 105)”, where the one or more devices that monitor may be “a device of the site management system, a device of the back office system, a device associated with the operator of machine”, etc.; where the one or more devices may “cause a calendar, of the technician, to be populated with a calendar event to inspect and/or repair the one or more components”).
While Zhang teaches output an indication of the prediction or health information to an operator interface, Zhang does not specifically teach outputting a visual indication of the prediction or health information. Additionally, while Zhang teaches historical operation data, Zhang does not teach wherein the historical operation comprises one or more of a forward distance traveled by a track of the tracked undercarriage, a reverse distance traveled by the track of the tracked undercarriage, a duration of operation by the tracked undercarriage, and a rotational torque associated with the track of the tracked undercarriage.
However, Johannsen teaches outputting a visual indication of the prediction or health information (Johannsen, Para. 0037 – where an “on-board computer” may “display wear information (e.g., to an operator of the machine 10)”, such as “safety messages regarding the state of the track assembly 14, an estimated operating time until service will be necessary, etc.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the predictive maintenance system of Zhang to include outputting a visual indication of the prediction or health information, as taught by Johannsen, in order to present the indication of the prediction of health information to the operator through a visual means as a method to alert the operator of a need for inspection or repair.
Zhang in view of Johannsen does not teach wherein the historical operation comprises one or more of a forward distance traveled by a track of the tracked undercarriage, a reverse distance traveled by the track of the tracked undercarriage, a duration of operation by the tracked undercarriage, and a rotational torque associated with the track of the tracked undercarriage
However, Mhadbi teaches wherein the historical operation comprises one or more of a forward distance traveled by a track of the tracked undercarriage, a reverse distance traveled by the track of the tracked undercarriage, a duration of operation by the tracked undercarriage (Mhadbi, Para. 0016-0023 and 0026 – where data used to train a “statistical model” include “service hours” and other objects used to derive “total travel time”, “travel hours per steering”, “travel hours per slope”, etc.; where the statistical model is used to predict wear of undercarriage components such as a track chain, a track roller, etc.), and a rotational torque associated with the track of the tracked undercarriage (Mhadbi, Para. 0016, 0019 and 0026 – where derived data of the components of the undercarriage used to train the statistical model includes “drive torque”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the predictive maintenance system including the above limitations of Zhang in view of Johannsen to include wherein the wherein the historical operation comprises one or more of a duration of operation by the tracked undercarriage; and a rotational torque associated with the track of the tracked undercarriage, as taught by Mhadbi, in order to determine historical operations and their impact on the wear of the tracked undercarriage to improve accuracy of the predictions of the model.
Claim(s) 16 is rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Johannsen, Mhadbi, and further in view of Jang.
In regards to Claim 16, Zhang in view of Johannsen and Mhadbi teaches the method of Claim 11, and Zhang teaches the historical inspection data (Zhang, Para. 0043-0044 – where an “inspection device” may provide “historical inspection data regarding historical inspections of machine” including “times and/or dates associated with when the historical inspections were performed”), but Zhang does not specifically teach wherein the historical inspection data is derived from a last known inspection data.
However, Jang teaches wherein the historical inspection data is derived from a last known inspection data (Jang, Para. 0044 – a controller generates a “machine application profile may be used to predict a potential failure of a component of machine”, where the profile is generated using “records of treatments and maintenance”, for example the controller “may check the last time this component was examined” when an activity that may cause wear is identified).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the method including the above limitations of Zhang in view of Johannsen and Mhadbi to include wherein the historical inspection data is derived from a last known inspection data, as taught by Jang, in order to use the most recent inspection data to prove a predictive maintenance system with the most up-to-date and accurate data.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Cho (Korean Patent App. Pub. No. 20230029386) teaches a method for predicting tire wear, and more particularly, to a method for predicting a real-vehicle test using real-vehicle and interior information capable of predicting a final result using an initial value of a real-vehicle test, wherein the initial value is determined according to an initial set mileage value.
Diekevers, et al. (U.S. Patent Application Pub. No. 2015/0337522) teaches a method and apparatus is disclosed for monitoring the status of machine components of a track-type mobile machine.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HELEN LI whose telephone number is (703)756-4719. The examiner can normally be reached Monday through Friday, from 9am to 5pm eastern.
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, Hunter Lonsberry can be reached at (571) 272-7298. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/H.L./Examiner, Art Unit 3665
/HUNTER B LONSBERRY/Supervisory Patent Examiner, Art Unit 3665