DETAILED ACTION
Claims 21-40 are pending. Claims 1-20 are cancelled.
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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 2/22/2026 has been entered.
Response to Arguments
Applicant’s arguments, filed 2/22/26, have been fully considered but are not persuasive, except where noted below.
Applicant’s comments regarding the objection to the specification (page 8) are noted and the specification is no longer objected to.
Applicant’s arguments regarding 35 U.S.C. § 112(a) (page 9) are persuasive and the claims are no longer rejected under that rationale.
Applicant’s arguments regarding 35 U.S.C. § 112(b) (page 9) are persuasive regarding claims 21, 25, 31 and 35. The arguments are not persuasive regarding claims 26 and 36 as detailed below in the current rejection under 35 U.S.C. § 112(b).
Applicant’s arguments regarding 35 U.S.C. § 101 (pages 9-13) are moot because the claims are no longer rejected under that statute.
For at least these reasons, the rejection of the claims is maintained.
Claim Rejections - 35 USC § 112
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.
Claim(s) 26-27 and 36-37 is/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 pre-AIA the applicant regards as the invention.
With regard to claim 26, this claim recites ‘comparing a first set of time series data associated with the first faulty batch with a second set of time series data associated with at least one batch different than the first batch; and identifying the at least one other batch having time series data similar to the first batch’ and it is unclear what the metes and bounds are of time series data similar to the first batch; see MPEP 2173.05.
With regard to claim 27, this claim recites ‘updating the set of time series data with the aggregated time series data’ and it is unclear how ‘the set of time series data’ are ‘updated’ with aggregated time series data; or if ‘the set of time series data with the aggregated time series data’ are somehow being updated. In addition, there is no antecedent basis for ‘the deviation’.
With regard to claim 36, this claim recites ‘comparing a first set of time series data associated with the first faulty batch with a second set of time series data associated with at least one other batch different than the first batch; and identifying the at least one batch having time series data similar to the first batch’ and it is unclear what the metes and bounds are of time series data similar to the first batch; see MPEP 2173.05.
With regard to claim 37, this claim recites language to claim 27 and is rejected based on the same rationale.
The dependent claims are also rejected under 35 U.S.C. § 112 as they inherit all of the characteristics of the claim from which they depend and none of the dependent claims provide a cure for the indefiniteness of the parent claims.
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 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 of this title, 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.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 21-25, 30-35 and 40 is/are rejected under 35 U.S.C. 103 as being unpatentable over Liao et al. U.S. Patent Publication No. 20160091393 (hereinafter Liao) in view of Lakhani et al. U.S. Patent Publication No. 20210390320 (hereinafter Lakhani) and further in view of Putman et al. U.S. Patent Publication No. 20190299536 (hereinafter Putman).
Regarding claim 21, Liao teaches computer implemented method [0030, Fig. 2 — A computer-implemented method is provided to provide warning or recommendation for manufacturing shop floor supervisors or operators on accumulated damage of the machine tools, by using automatic clustering of machining processes and particle filter based prognostics using time series data of the machine tools.] comprising:
receiving time series data from one or more sensors of a facility, the time-series data associated with a first workflow level of a manufacturing process of the facility [0014 — A method and a system for detecting machine tool wear or anomaly, predicting machine tool remaining useful life, and planning in manufacturing shop floor us provided; 0028-0030, Figs. 1-2 — A Web-based server (13) collects operational data of a machine (11) gathered through a sensor (12) installed on or close to the machine (11)… Operational data, such as a time series of positional parameters and movement parameters of a machine tool, are collected and retrieved (31). The operation data are pre-processed by indexing or adding a time stamp. A machine is identified, usually by using the machine's unique IP address. — Note that manufacturing involves at least one workflow level.];
aggregating the time series data to generate statistical data associated with operations at the first workflow level, wherein the statistical data comprises at least one of averages over time intervals, rates of change, or derivative values of the time series data of one or more sensed parameters associated with the manufacturing process [0014-0016 — the aggregated axes traverse and the spindle load verse rotating speed are incorporated to provide a measure of the wear on various axes in the machine... Similar processes are clustered according to the similarity of the processes. Tool wear or degradation is detected by characterizing a trend of change in a parameter from the one or more clusters of machining processes performed by the machine tool. The remaining useful life of the machine tool is predicted; 0028-0031 — programs or modules (15) includes an aggregates of modules that implements a sets of functions, including operational data processing, machine and tool process identification, process clustering, machine tool degradation detection, the remaining useful life prediction, outlier detection, and manufacturing shop floor planning analysis algorithms… processes thus identified are further clustered into groups or clusters according to similarity of the processes (33); 0042 —clustering a process allows detecting a trend of the process, monitoring outliers, as described supra. FIG. 4 is flow diagram showing a computer-implemented method to automatically cluster machining processes into clusters; 0086 — The aggregate axes traverse provides another measure of wear on various axes in a machine. In a further embodiment, information on aggregate axes traverse are used to provide an estimate of the way damage. The aggregate axes traverses are compared between two machines.; 0049-0050 — the trend of the change in a parameter in a cluster of machining processes performed by the machine tool is detected by a monotonicity test… F represents a parameter or feature and d/dF is the derivative (derivative values)];
comparing the aggregated time series data with a set of time-series data stored in a database; detecting one or more anomalies in at least one of the first workflow level and the second workflow level based on a comparison of the aggregated time series data with a set of time series data stored in the database [0058-0063 — Anomaly detection is an important aspect for a self-aware system. An anomaly is an exception or deviation from a typical pattern. An anomaly under the context of a manufacturing shop is an abnormal machine process, and may manifest through unusual, uncustomary exceptional, or extraordinary occurrence of the tool parameters, including a rare choice of a machine tool, unusually high or low spindle power in a machining process compare to similar machining processes, unusual high or low spindle speed in a machining process compare to similar machining processes, an uncharacteristic tool path in a machining process compare to similar machining processes… a method for detecting an anomaly of a machine tool is provided. A stream of operational data comprising positional parameters and movement parameters of machining processes performed by the machine tool are collected. The distribution patterns of the operational data are characterized by multiple analytical methods. New operational data is collected and compared to the distribution patterns from the multiple analytical methods. The presence of one or more outliers against the distribution patterns of the analytical methods are determined. The number of the outliers are compared to a pre-determined threshold; 0087 — Warnings or recommendations based upon the usage and performance comparison between machines may be sent to manufacturing shop supervisors, operators, maintenance crews, or other related personnel. Measures can be subsequently taken to address the imbalance of the machine usage and wear in accordance to the objective estimate of machine wear and damage accumulation. As a result, manufacturing shop can move from a scheduled maintenance to a condition-based maintenance that more closely reflects the damage accumulation].
But Liao fails to clearly specify a first workflow level and a second workflow level of a plurality of workflow levels and correlating the one or more detected anomalies in the at least one of the first workflow level and the second workflow level based at least on one or more historical patterns associated with one or more historical manufacturing processes; determining at least one action by using a trained machine learning model for the at least one of the first workflow level and the second workflow level, wherein the at least one action comprises controlling at least one actuator of the manufacturing process to modify one or more parameters of the manufacturing process, wherein controlling comprises issuing control signals to the actuator, and wherein the trained machine learning model is trained based at least on the one or more historical patterns; and performing the at least one action at the at least one of the first workflow level and the second workflow level to modify the one or more parameters of the manufacturing process during execution of the manufacturing process to dynamically adjust the manufacturing process at least at one or both of the first workflow level and the second workflow level.
However, Lakhani teaches a first workflow level and a second workflow level of a plurality of workflow levels [0129-0132, Fig. 8 — FIG. 8 illustrates a scheme illustrating different levels of providing manufacture support aligned with the ISA95 standard. A level 0 illustrates a physical production process. In level 1, the components, such as sensors, pumps etc. of the physical production process are defined. The physical process is sensed by means of sensors and the production process may be manipulated. Level 2 relates to automation systems. Level 2 may be defined as a factory or unit operation level. In level 2, monitoring and supervisory control and automated control of the process is obtained. By implementing levels 1 and 2, manufacturing control is achieved. The manufacturing control involves basic control, supervisory control, process sensing and process manipulation].
Liao and Lakhani are analogous art. They relate to manufacturing systems.
Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to modify the above method, as taught by Liao, by incorporating the above limitations, as taught by Lakhani.
One of ordinary skill in the art would have been motivated to do this modification in order to detect anomalies at multiple workflow levels, not just a single workflow level. In addition, it would be obvious to one having ordinary skill in the art to simply substitute the known multiple workflow levels of Lakhani for the known workflow level of Liao for the predictable result of a method able to detect anomalies in a muti-workflow system.
But the combination of Liao and Lakhani fails to clearly specify correlating the one or more detected anomalies in the at least one of the first workflow level and the second workflow level based at least on one or more historical patterns associated with one or more historical manufacturing processes; determining at least one action by using a trained machine learning model for the at least one of the first workflow level and the second workflow level, wherein the at least one action comprises controlling at least one actuator of the manufacturing process to modify one or more parameters of the manufacturing process, wherein controlling comprises issuing control signals to the actuator, and wherein the trained machine learning model is trained based at least on the one or more historical patterns; and performing the at least one action at the at least one of the first workflow level and the second workflow level to modify the one or more parameters of the manufacturing process during execution of the manufacturing process to dynamically adjust the manufacturing process at least at one or both of the first workflow level and the second workflow level.
However, Putnam teaches correlating the one or more detected anomalies in the at least one of the first workflow level and the second workflow level based at least on one or more historical patterns associated with one or more historical manufacturing processes; determining at least one action by using a trained machine learning model for the at least one of the first workflow level and the second workflow level, wherein the at least one action comprises controlling at least one actuator of the manufacturing process to modify one or more parameters of the manufacturing process, wherein controlling comprises issuing control signals to the actuator, and wherein the trained machine learning model is trained based at least on the one or more historical patterns; and performing the at least one action at the at least one of the first workflow level and the second workflow level to modify the one or more parameters of the manufacturing process during execution of the manufacturing process to dynamically adjust the manufacturing process at least at one or both of the first workflow level and the second workflow level [0007-0009 — determine a correlation between the identified anomaly and one or more print parameters using a second artificial intelligence algorithm; 0071 — information on the correlations can be used to train one of more AI (artificial intelligence) mechanisms as described herein; 0077-0090, Fig. 6 — an example of an additive manufacturing printing operation using AIFC, in accordance with some embodiments of the disclosed subject matter; 0097-0104 — FIG. 8 shows, an example 800 of a training process for learning anomaly patterns and anomaly rates based on different infill density and infill patterns and how those anomaly patterns and anomaly rates affect the printed object's mechanical properties… Once image analyzer 180 has learned how different anomaly rates and patterns and the identified print parameters (e.g., different infill density and infill patterns) affect the mechanical properties of an object, the image analyzer can adaptively adjust the values for the identified print parameters during a print job (e.g., at a layer level) to achieve desired mechanical properties. For example, image analyzer 180 can detect that printed layers of a partially printed object have a certain anomaly rate and pattern that would likely result in sub-par mechanical properties for the printed object once completed if the infill density and infill pattern were not adjusted. Image analyzer 180 can then adjust the infill rate and infill pattern print parameters for the next and/or any subsequent layers to achieve the desired mechanical properties, while also trying to reduce the occurrence of anomalies — Note that manufacturing involves at least one workflow level; 0028 — Other aspects of print head(s) 140 and/or build plate(s) 150 that can be controlled include, for example, paths that print head(s) 140 and/or build plate(s) 150 follow during movement, amount(s) that the print head(s) and/or build plate(s) 150 move with respect to the other along the Z-axis dimension when transitioning between layers of a production design, orientation(s) of print head(s) 140 and/or build plate(s) 150 with respect to the other, speed(s) of movement of print head(s) 140 and/or build plate(s) 150 (actuators); 0031 — communication between control module 160 and other components of additive manufacturing system 100, and/or communication between control module 160 and other components within additive manufacturing printer 115, can use any suitable communication technologies, such as analog technologies (e.g., relay logic), digital technologies (e.g., RS232, ethernet, or wireless), network technologies (e.g., local area network (LAN), a wide area network (WAN), the Internet), Bluetooth technologies, Near-field communication technologies, Secure RF technologies, and/or any other suitable communication technologies (signals); 0067-0073 — the image analyzer can communicate the discovered correlations and/or instructions for adaptively adjusting print parameter settings to numerical control code generator 110, control module 160 and/or to any other device. The numerical control code generator 110 and/or control module 160 can then use the information to make adjustments to the print parameters in the numerical control code for any subsequent layers of an object that is currently being printed; 0104 — Once image analyzer 180 has learned how different anomaly rates and patterns and the identified print parameters (e.g., different infill density and infill patterns) affect the mechanical properties of an object, the image analyzer can adaptively adjust the values for the identified print parameters during a print job (e.g., at a layer level) to achieve desired mechanical properties].
Liao, Lakhani and Putman are analogous art. They relate to manufacturing systems.
Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to modify the above method, as taught by the combination of Liao and Lakhani, by incorporating the above limitations, as taught by Putman.
One of ordinary skill in the art would have been motivated to do this modification in order to improve the manufacturing process by taking corrective action, as suggested by Putman [0005-0006, 0019].
Regarding claim 22, the combination of Liao, Lakhani and Putman teaches all the limitations of the base claims as outlined above.
Further, Liao teaches receiving one or more measurement values from the one or more sensors in the facility [0014 — A method and a system for detecting machine tool wear or anomaly, predicting machine tool remaining useful life, and planning in manufacturing shop floor us provided; 0028-0030, Figs. 1-2 — A Web-based server (13) collects operational data of a machine (11) gathered through a sensor (12) installed on or close to the machine (11)… Operational data, such as a time series of positional parameters and movement parameters of a machine tool, are collected and retrieved (31). The operation data are pre-processed by indexing or adding a time stamp. A machine is identified, usually by using the machine's unique IP address.].
Further, Putnam teaches receiving one or more measurement values from the one or more sensors in the facility, and wherein the one or more measurement values are related to at least one of: a pressure, a temperature, and a flow rate associated with the manufacturing process [0030-0033 — additive manufacturing printer 115 can also include other components, for example, a temperature sensor].
Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to simply substitute known pressure measurements, as taught by Putnam, for the known senor measurements of Liao for the predictable result of a method able to detect anomalies in a muti-workflow system using pressure sensor measurements.
Regarding claim 23, the combination of Liao, Lakhani and Putman teaches all the limitations of the base claims as outlined above.
Further, Liao teaches determining statistical values or average values of the time series data based on statistical aggregations [0042-0046 — For each additional process, the similarity to the initial group of the processes is ascertained by determining the Hotelling's T-squared or T2 statistics for the matching measure ]; and
providing a context for the aggregated time series data [0028-0030, Figs. 1-2 — A Web-based server (13) collects operational data of a machine (11) gathered through a sensor (12) installed on or close to the machine (11)… Operational data, such as a time series of positional parameters and movement parameters of a machine tool, are collected and retrieved (31). The operation data are pre-processed by indexing or adding a time stamp. A machine is identified, usually by using the machine's unique IP address.] and one or more settings of the manufacturing process [0032 — machine tool operational data includes machine tool identification parameter, positional parameters, and movement parameters… movement parameter can be spindle speed, spindle speed override, feed rate, feed rate override, spindle load, X-axis load, Y-axis load, Z-axis load, and spindle power. These parameters, or variables, describe and define the machine tool's position, movement, and usage].
Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to simply substitute known settings of the manufacturing process, as taught by Liao, for the known context data of Liao for the predictable result of a method able to detect anomalies in a muti-workflow system using setting data and thus able to better capture the effect of manufacturing settings.
Regarding claim 24, the combination of Liao, Lakhani and Putman teaches all the limitations of the base claims as outlined above.
Further, Liao teaches identifying at least one set of time series data of the one or more historical manufacturing processes using a confidence level; and determining a similarity between the at least one set of time series data and the aggregated time series data [0042-0045 — Process clustering refers to grouping, or clustering, similar machining processes in a group or cluster… For each additional process, the similarity to the initial group of the processes is ascertained by determining the Hotelling's T-squared or T2 statistics for the matching measure of the additional process… where F.sub.α(p,N−p) is the 100α% confidence level of F-distribution with p and N−p degrees of freedom (54).].
Regarding claim 25, the combination of Liao, Lakhani and Putman teaches all the limitations of the base claims as outlined above.
Further, Liao teaches computing a difference between the aggregated time series data and one or more values of the set of time series data; determining that the computed difference exceeds a threshold value; and in response to the computed difference exceeding the threshold value, identifying an anomaly at the at least one of the first workflow level and the second workflow level [0058-0063 — Anomaly detection is an important aspect for a self-aware system. An anomaly is an exception or deviation (difference) from a typical pattern. An anomaly under the context of a manufacturing shop is an abnormal machine process, and may manifest through unusual, uncustomary exceptional, or extraordinary occurrence of the tool parameters, including a rare choice of a machine tool, unusually high or low spindle power in a machining process compare to similar machining processes, unusual high or low spindle speed in a machining process compare to similar machining processes, an uncharacteristic tool path in a machining process compare to similar machining processes… a method for detecting an anomaly of a machine tool is provided. A stream of operational data comprising positional parameters and movement parameters of machining processes performed by the machine tool are collected. The distribution patterns of the operational data are characterized by multiple analytical methods. New operational data is collected and compared to the distribution patterns from the multiple analytical methods. The presence of one or more outliers against the distribution patterns of the analytical methods are determined. The number of the outliers are compared to a pre-determined threshold; 0040 — The ICP algorithm optimizes the operation matrix of T, b and c so that the difference (denoted as d) between transform and target is minimized. The difference shows the extent to which source and target are different. The smaller the difference, the better the match/overlap between source and target. The difference between the tool path shapes in shape spaces is denoted as d.sub.s, and the difference between the movement parameter shapes in the parameter spaces is denoted as d.sub.p; 0050 — F represents a parameter or feature and d/dF is the derivative (63). The maximum value of Monotonicity equals to 1 only if the feature is monotonically increasing. The value of monotonicity indicates the increasing trend of the spindle power, which indirectly indicates the degradation of the cutting tool. A threshold of the monotonicity value can be set up according to a set of factors, including the nature of the tools, the effect of tool failure on workflows, among others (64).].
Regarding claim 30, the combination of Liao, Lakhani and Putman teaches all the limitations of the base claims as outlined above.
Further, Liao teaches predicting, based on the aggregated time series data, an event at the at least one of the first workflow level and the second workflow level [0014-0016 — A method and a system for detecting machine tool wear or anomaly, predicting machine tool remaining useful life, and planning in manufacturing shop floor us provided; 0028-0030, Figs. 1-2 — a functional block diagram showing a computer-implemented system for detecting degradation and predicting failure of a machine tool… A Web-based server (13) collects operational data of a machine (11) gathered through a sensor (12) installed on or close to the machine (11)… Operational data, such as a time series of positional parameters and movement parameters of a machine tool, are collected and retrieved (31). The operation data are pre-processed by indexing or adding a time stamp. A machine is identified, usually by using the machine's unique IP address.]; and identifying one or more corrective actions based on the predicted event [0085-0087 — A histogram of the spindle loads weighted by the time spent at various spindle speeds is plotted and compared for two machines, which provides a relative estimate of remaining useful life of the spindle bearings. This information is fed back to a scheduling system depending on the shop's maintenance policy. For example, if all machines will be taken down around the same time for service, the machine with less spindle damage may be scheduled for more jobs until the spindle damages are balanced out prior to the service… Measures can be subsequently taken to address the imbalance of the machine usage and wear in accordance to the objective estimate of machine wear and damage accumulation].
Regarding claim 31, Liao teaches a machine-readable storage device having instructions for execution by a processor of a machine to cause the processor to perform operations to perform a method [0028-0030, Fig. 2 — a central processing unit… server (14) can each include one or more modules for carrying out the embodiments disclosed herein… . The various implementations of the source code and object and byte codes can be held on a computer-readable storage medium, such as a floppy disk, hard drive, digital video disk (DVD), random access memory (RAM), read-only memory (ROM) and similar storage mediums… A computer-implemented method is provided to provide warning or recommendation for manufacturing shop floor supervisors or operators on accumulated damage of the machine tools, by using automatic clustering of machining processes and particle filter based prognostics using time series data of the machine tools.], the operations comprising:
receiving time series data from one or more sensors of a facility, the time-series data associated with a first workflow level of a manufacturing process of the facility [0014 — A method and a system for detecting machine tool wear or anomaly, predicting machine tool remaining useful life, and planning in manufacturing shop floor us provided; 0028-0030, Figs. 1-2 — A Web-based server (13) collects operational data of a machine (11) gathered through a sensor (12) installed on or close to the machine (11)… Operational data, such as a time series of positional parameters and movement parameters of a machine tool, are collected and retrieved (31). The operation data are pre-processed by indexing or adding a time stamp. A machine is identified, usually by using the machine's unique IP address. — Note that manufacturing involves at least one workflow level.];
aggregating the time series data to generate statistical data associated with operations at the first workflow level, wherein the statistical data comprises at least one of averages over time intervals, rates of change, or derivative values of the time series data of one or more sensed parameters associated with the manufacturing process [0014-0016 — the aggregated axes traverse and the spindle load verse rotating speed are incorporated to provide a measure of the wear on various axes in the machine... Similar processes are clustered according to the similarity of the processes. Tool wear or degradation is detected by characterizing a trend of change in a parameter from the one or more clusters of machining processes performed by the machine tool. The remaining useful life of the machine tool is predicted; 0028-0031 — programs or modules (15) includes an aggregates of modules that implements a sets of functions, including operational data processing, machine and tool process identification, process clustering, machine tool degradation detection, the remaining useful life prediction, outlier detection, and manufacturing shop floor planning analysis algorithms… processes thus identified are further clustered into groups or clusters according to similarity of the processes (33); 0042 —clustering a process allows detecting a trend of the process, monitoring outliers, as described supra. FIG. 4 is flow diagram showing a computer-implemented method to automatically cluster machining processes into clusters; 0086 — The aggregate axes traverse provides another measure of wear on various axes in a machine. In a further embodiment, information on aggregate axes traverse are used to provide an estimate of the way damage. The aggregate axes traverses are compared between two machines.; 0049-0050 — the trend of the change in a parameter in a cluster of machining processes performed by the machine tool is detected by a monotonicity test… F represents a parameter or feature and d/dF is the derivative (derivative values)];
comparing the aggregated time series data with a set of time-series data stored in a database; detecting one or more anomalies in at least one of the first workflow level and the second workflow level based on a comparison of the aggregated time series data with a set of time series data stored in the database [0058-0063 — Anomaly detection is an important aspect for a self-aware system. An anomaly is an exception or deviation from a typical pattern. An anomaly under the context of a manufacturing shop is an abnormal machine process, and may manifest through unusual, uncustomary exceptional, or extraordinary occurrence of the tool parameters, including a rare choice of a machine tool, unusually high or low spindle power in a machining process compare to similar machining processes, unusual high or low spindle speed in a machining process compare to similar machining processes, an uncharacteristic tool path in a machining process compare to similar machining processes… a method for detecting an anomaly of a machine tool is provided. A stream of operational data comprising positional parameters and movement parameters of machining processes performed by the machine tool are collected. The distribution patterns of the operational data are characterized by multiple analytical methods. New operational data is collected and compared to the distribution patterns from the multiple analytical methods. The presence of one or more outliers against the distribution patterns of the analytical methods are determined. The number of the outliers are compared to a pre-determined threshold; 0087 — Warnings or recommendations based upon the usage and performance comparison between machines may be sent to manufacturing shop supervisors, operators, maintenance crews, or other related personnel. Measures can be subsequently taken to address the imbalance of the machine usage and wear in accordance to the objective estimate of machine wear and damage accumulation. As a result, manufacturing shop can move from a scheduled maintenance to a condition-based maintenance that more closely reflects the damage accumulation].
But Liao fails to clearly specify a first workflow level and a second workflow level of a plurality of workflow levels and correlating the one or more detected anomalies in the at least one of the first workflow level and the second workflow level based at least on one or more historical patterns associated with one or more historical manufacturing processes; determining at least one action by using a trained machine learning model for the at least one of the first workflow level and the second workflow level, wherein the at least one action comprises controlling at least one actuator of the manufacturing process to modify one or more parameters of the manufacturing process, wherein controlling comprises issuing control signals to the actuator, and wherein the trained machine learning model is trained based at least on the one or more historical patterns; and performing the at least one action at the at least one of the first workflow level and the second workflow level to modify the one or more parameters of the manufacturing process during execution of the manufacturing process to dynamically adjust the manufacturing process at least at one or both of the first workflow level and the second workflow level.
However, Lakhani teaches a first workflow level and a second workflow level of a plurality of workflow levels [0129-0132, Fig. 8 — FIG. 8 illustrates a scheme illustrating different levels of providing manufacture support aligned with the ISA95 standard. A level 0 illustrates a physical production process. In level 1, the components, such as sensors, pumps etc. of the physical production process are defined. The physical process is sensed by means of sensors and the production process may be manipulated. Level 2 relates to automation systems. Level 2 may be defined as a factory or unit operation level. In level 2, monitoring and supervisory control and automated control of the process is obtained. By implementing levels 1 and 2, manufacturing control is achieved. The manufacturing control involves basic control, supervisory control, process sensing and process manipulation].
Liao and Lakhani are analogous art. They relate to manufacturing systems.
Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to modify the above machine-readable storage device, as taught by Liao, by incorporating the above limitations, as taught by Lakhani.
One of ordinary skill in the art would have been motivated to do this modification in order to detect anomalies at multiple workflow levels, not just a single workflow level. In addition, it would be obvious to one having ordinary skill in the art to simply substitute the known multiple workflow levels of Lakhani for the known workflow level of Liao for the predictable result of a machine-readable storage device able to detect anomalies in a muti-workflow system.
But the combination of Liao and Lakhani fails to clearly specify correlating the one or more detected anomalies in the at least one of the first workflow level and the second workflow level based at least on one or more historical patterns associated with one or more historical manufacturing processes; determining at least one action by using a trained machine learning model for the at least one of the first workflow level and the second workflow level, wherein the at least one action comprises controlling at least one actuator of the manufacturing process to modify one or more parameters of the manufacturing process, wherein controlling comprises issuing control signals to the actuator, and wherein the trained machine learning model is trained based at least on the one or more historical patterns; and performing the at least one action at the at least one of the first workflow level and the second workflow level to modify the one or more parameters of the manufacturing process during execution of the manufacturing process to dynamically adjust the manufacturing process at least at one or both of the first workflow level and the second workflow level.
However, Putnam teaches correlating the one or more detected anomalies in the at least one of the first workflow level and the second workflow level based at least on one or more historical patterns associated with one or more historical manufacturing processes; determining at least one action by using a trained machine learning model for the at least one of the first workflow level and the second workflow level, wherein the at least one action comprises controlling at least one actuator of the manufacturing process to modify one or more parameters of the manufacturing process, wherein controlling comprises issuing control signals to the actuator, and wherein the trained machine learning model is trained based at least on the one or more historical patterns; and performing the at least one action at the at least one of the first workflow level and the second workflow level to modify the one or more parameters of the manufacturing process during execution of the manufacturing process to dynamically adjust the manufacturing process at least at one or both of the first workflow level and the second workflow level [0007-0009 — determine a correlation between the identified anomaly and one or more print parameters using a second artificial intelligence algorithm; 0071 — information on the correlations can be used to train one of more AI (artificial intelligence) mechanisms as described herein; 0077-0090, Fig. 6 — an example of an additive manufacturing printing operation using AIFC, in accordance with some embodiments of the disclosed subject matter; 0097-0104 — FIG. 8 shows, an example 800 of a training process for learning anomaly patterns and anomaly rates based on different infill density and infill patterns and how those anomaly patterns and anomaly rates affect the printed object's mechanical properties… Once image analyzer 180 has learned how different anomaly rates and patterns and the identified print parameters (e.g., different infill density and infill patterns) affect the mechanical properties of an object, the image analyzer can adaptively adjust the values for the identified print parameters during a print job (e.g., at a layer level) to achieve desired mechanical properties. For example, image analyzer 180 can detect that printed layers of a partially printed object have a certain anomaly rate and pattern that would likely result in sub-par mechanical properties for the printed object once completed if the infill density and infill pattern were not adjusted. Image analyzer 180 can then adjust the infill rate and infill pattern print parameters for the next and/or any subsequent layers to achieve the desired mechanical properties, while also trying to reduce the occurrence of anomalies — Note that manufacturing involves at least one workflow level; 0028 — Other aspects of print head(s) 140 and/or build plate(s) 150 that can be controlled include, for example, paths that print head(s) 140 and/or build plate(s) 150 follow during movement, amount(s) that the print head(s) and/or build plate(s) 150 move with respect to the other along the Z-axis dimension when transitioning between layers of a production design, orientation(s) of print head(s) 140 and/or build plate(s) 150 with respect to the other, speed(s) of movement of print head(s) 140 and/or build plate(s) 150 (actuators); 0031 — communication between control module 160 and other components of additive manufacturing system 100, and/or communication between control module 160 and other components within additive manufacturing printer 115, can use any suitable communication technologies, such as analog technologies (e.g., relay logic), digital technologies (e.g., RS232, ethernet, or wireless), network technologies (e.g., local area network (LAN), a wide area network (WAN), the Internet), Bluetooth technologies, Near-field communication technologies, Secure RF technologies, and/or any other suitable communication technologies (signals); 0067-0073 — the image analyzer can communicate the discovered correlations and/or instructions for adaptively adjusting print parameter settings to numerical control code generator 110, control module 160 and/or to any other device. The numerical control code generator 110 and/or control module 160 can then use the information to make adjustments to the print parameters in the numerical control code for any subsequent layers of an object that is currently being printed; 0104 — Once image analyzer 180 has learned how different anomaly rates and patterns and the identified print parameters (e.g., different infill density and infill patterns) affect the mechanical properties of an object, the image analyzer can adaptively adjust the values for the identified print parameters during a print job (e.g., at a layer level) to achieve desired mechanical properties].
Liao, Lakhani and Putman are analogous art. They relate to manufacturing systems.
Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to modify the above machine-readable storage device, as taught by the combination of Liao and Lakhani, by incorporating the above limitations, as taught by Putman.
One of ordinary skill in the art would have been motivated to do this modification in order to improve the manufacturing process by taking corrective action, as suggested by Putman [0005-0006, 0019].
Regarding claim 32, the combination of Liao, Lakhani and Putman teaches all the limitations of the base claims as outlined above and this claim is otherwise rejected under the same rationale as claim 22.
Regarding claim 33, the combination of Liao, Lakhani and Putman teaches all the limitations of the base claims as outlined above and this claim is otherwise rejected under the same rationale as claim 23.
Regarding claim 34, the combination of Liao, Lakhani and Putman teaches all the limitations of the base claims as outlined above and this claim is otherwise rejected under the same rationale as claim 24.
Regarding claim 35, the combination of Liao, Lakhani and Putman teaches all the limitations of the base claims as outlined above and this claim is otherwise rejected under the same rationale as claim 25.
Regarding claim 40, the combination of Liao, Lakhani and Putman teaches all the limitations of the base claims as outlined above and this claim is otherwise rejected under the same rationale as claim 30.
Claim(s) 28 and 38 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Liao, Lakhani and Putnam in view of Ghosh et al. U.S. Patent Publication No. 20200097921 (hereinafter Ghosh).
Regarding claim 28, the combination of Liao, Lakhani and Putman teaches all the limitations of the base claims as outlined above.
Further, Liao teaches time series data [0030-0031 — A Web-based server (13) collects operational data of a machine (11) gathered through a sensor (12) installed on or close to the machine (11)… Operational data, such as a time series of positional parameters and movement parameters of a machine tool, are collected and retrieved (31).].
Further, Putnam teaches obtaining the trained machine learning model based on a training using the set of time series data stored in the database, [0007-0009 — determine a correlation between the identified anomaly and one or more print parameters using a second artificial intelligence algorithm; 0071 — information on the correlations can be used to train one of more AI (artificial intelligence) mechanisms as described herein; 0077-0090, Fig. 6 — an example of an additive manufacturing printing operation using AIFC, in accordance with some embodiments of the disclosed subject matter; 0097-0104 — FIG. 8 shows, an example 800 of a training process for learning anomaly patterns and anomaly rates based on different infill density and infill patterns and how those anomaly patterns and anomaly rates affect the printed object's mechanical properties… Once image analyzer 180 has learned how different anomaly rates and patterns and the identified print parameters (e.g., different infill density and infill patterns) affect the mechanical properties of an object, the image analyzer can adaptively adjust the values for the identified print parameters during a print job (e.g., at a layer level) to achieve desired mechanical properties. For example, image analyzer 180 can detect that printed layers of a partially printed object have a certain anomaly rate and pattern that would likely result in sub-par mechanical properties for the printed object once completed if the infill density and infill pattern were not adjusted. Image analyzer 180 can then adjust the infill rate and infill pattern print parameters for the next and/or any subsequent layers to achieve the desired mechanical properties, while also trying to reduce the occurrence of anomalies — Note that manufacturing involves at least one workflow level].
But the combination of Liao, Lakhani and Putman fails to clearly specify data is labelled with at least one of: a context of the one or more historical manufacturing processes and one or more historical actions.
However, Ghosh teaches data is labelled with at least one of: a context of the one or more historical manufacturing processes and one or more historical actions [0052 — . Examples of equipment 152 herein may include vehicles, appliances, construction equipment, manufacturing equipment; 0072-0079 — (g) Repair history: for training data, the computing device may extract all the details of prior repair processes (e.g., system(s), subsystem(s), component(s), part(s), and repair action(s) performed), and use these details as the target labels that are to be learned by the machine learning model.].
Liao, Lakhani, Putman and Ghosh are analogous art. They relate to manufacturing systems.
Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to modify the above method, as taught by the combination of Liao, Lakhani and Putman by incorporating the above limitations, as taught by Ghosh.
One of ordinary skill in the art would have been motivated to do this modification in order to more easily identify the relevant data, particularly a required repair action, as suggested by Ghosh [0072-0079].
Regarding claim 38, the combination of Liao, Lakhani and Putman teaches all the limitations of the base claims as outlined above and this claim is otherwise rejected under the same rationale as claim 28.
Claim(s) 29 and 39 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Liao, Lakhani and Putnam in view of Hood et al. U.S. Patent Publication No. 20080082186 A1 (hereinafter Hood).
Regarding claim 29, the combination of Liao, Lakhani and Putman teaches all the limitations of the base claims as outlined above.
Further, Liao teaches time series data [0030-0031 — A Web-based server (13) collects operational data of a machine (11) gathered through a sensor (12) installed on or close to the machine (11)… Operational data, such as a time series of positional parameters and movement parameters of a machine tool, are collected and retrieved (31).].
Further, Lakhani teaches the first operation corresponding to the first workflow level and the second operation corresponding to the second workflow level [0129-0132, Fig. 8 — FIG. 8 illustrates a scheme illustrating different levels of providing manufacture support aligned with the ISA95 standard. A level 0 illustrates a physical production process. In level 1, the components, such as sensors, pumps etc. of the physical production process are defined. The physical process is sensed by means of sensors and the production process may be manipulated. Level 2 relates to automation systems. Level 2 may be defined as a factory or unit operation level. In level 2, monitoring and supervisory control and automated control of the process is obtained. By implementing levels 1 and 2, manufacturing control is achieved. The manufacturing control involves basic control, supervisory control, process sensing and process manipulation].
Further, Putnam teaches determining the at least one action by the trained machine learning model for the at least one of the first workflow level and the second workflow level is based on at least one historical action associated with the set of data [0007-0009 — determine a correlation between the identified anomaly and one or more print parameters using a second artificial intelligence algorithm; 0071 — information on the correlations can be used to train one of more AI (artificial intelligence) mechanisms as described herein; 0077-0090, Fig. 6 — an example of an additive manufacturing printing operation using AIFC, in accordance with some embodiments of the disclosed subject matter; 0097-0104 — FIG. 8 shows, an example 800 of a training process for learning anomaly patterns and anomaly rates based on different infill density and infill patterns and how those anomaly patterns and anomaly rates affect the printed object's mechanical properties… Once image analyzer 180 has learned how different anomaly rates and patterns and the identified print parameters (e.g., different infill density and infill patterns) affect the mechanical properties of an object, the image analyzer can adaptively adjust the values for the identified print parameters during a print job (e.g., at a layer level) to achieve desired mechanical properties. For example, image analyzer 180 can detect that printed layers of a partially printed object have a certain anomaly rate and pattern that would likely result in sub-par mechanical properties for the printed object once completed if the infill density and infill pattern were not adjusted. Image analyzer 180 can then adjust the infill rate and infill pattern print parameters for the next and/or any subsequent layers to achieve the desired mechanical properties, while also trying to reduce the occurrence of anomalies — Note that manufacturing involves at least one workflow level].
But the combination of Liao, Lakhani and Putman fails to clearly specify the operation corresponding to the workflow level comprises at least one of: packaging operations, warehousing operations, and shipping operations.
However, Hood teaches the operation corresponding to the workflow level comprises at least one of: packaging operations, warehousing operations, and shipping operations [0046 — the logic for a module that controls a motion axis in a high speed packaging machine might need to execute every 10 milliseconds].
Liao, Lakhani, Putman and Hood are analogous art. They relate to manufacturing systems.
Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to simply substitute known packaging operations, as taught by Hood, for the known operations of Liao for the predictable result of a method able to detect anomalies in a manufacturing system that comprises packaging operations.
Regarding claim 39, the combination of Liao, Lakhani and Putman teaches all the limitations of the base claims as outlined above and this claim is otherwise rejected under the same rationale as claim 29.
Citation of Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Walzenbach et al. U.S. Patent Publication No. 20230004148 discloses a system for controlling chemical plants where data are aggregated using a sum, an average or a mode.
Note that any citations to specific, pages, columns, lines, or figures in the prior art references and any interpretation of the reference should not be considered to be limiting in any way. A reference is relevant for all it contains and may be relied upon for all that it would have reasonably suggested to one having ordinary skill in the art. See MPEP 2123.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BERNARD G. LINDSAY whose telephone number is (571)270-0665. The examiner can normally be reached Monday through Friday from 8:30 AM to 5:30 PM EST.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Mohammad Ali can be reached on (571)272-4105. 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 Patent Center. Status information for published applications may be obtained from Patent Center. Status information for unpublished applications is available through Patent Center for authorized users only. Should you have questions about access to Patent Center, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant may call the examiner or use the USPTO Automated Interview Request (AIR) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/BERNARD G LINDSAY/
Primary Examiner, Art Unit 2119