Prosecution Insights
Last updated: April 19, 2026
Application No. 18/540,455

Two-Tier Prognostic Model for Explainable Remaining Useful Life Prediction

Non-Final OA §103
Filed
Dec 14, 2023
Examiner
OGG, DAVID EARL
Art Unit
2119
Tech Center
2100 — Computer Architecture & Software
Assignee
Percev LLC
OA Round
1 (Non-Final)
83%
Grant Probability
Favorable
1-2
OA Rounds
2y 8m
To Grant
95%
With Interview

Examiner Intelligence

Grants 83% — above average
83%
Career Allow Rate
241 granted / 290 resolved
+28.1% vs TC avg
Moderate +12% lift
Without
With
+12.1%
Interview Lift
resolved cases with interview
Typical timeline
2y 8m
Avg Prosecution
27 currently pending
Career history
317
Total Applications
across all art units

Statute-Specific Performance

§101
13.2%
-26.8% vs TC avg
§103
41.0%
+1.0% vs TC avg
§102
10.9%
-29.1% vs TC avg
§112
30.9%
-9.1% vs TC avg
Black line = Tech Center average estimate • Based on career data from 290 resolved cases

Office Action

§103
DETAILED ACTION 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 . Claims 1-26 are pending. 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. The factual inquiries 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 non-obviousness. Claim(s) 1-2, 5-9, 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, “A Probabilistic Framework for Remaining Useful Life Prediction of Bearings”, 2021, IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, VOL. 70, pp 1-12 (hereinafter Wang) in view of Harding et al, Chinese Patent Num CN105741005A (hereinafter Harding) in view of Xia et al, “A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks”, June 2019, IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, VOL. 15, NO. 6, pp 3703-3710 (hereinafter Xia). Claim 1 Wang teaches a method for predicting remaining useful life for industrial equipment (Wang, sec IV. A – A method for predicting the remaining service life of a rolling element bearing/”industrial equipment”.), the method comprising: monitoring machine sensor data for the industrial equipment in an industrial environment using at least one sensor (Wang, sec VII. A – Obtaining vibration signals/”machine sensor data” by using an accelerometer sensor.); applying a model implemented by a computing device by executing a set of instructions from a non-transitory machine readable memory using a processor of the computing device; and wherein the model receives as input sensor data comprising the machine sensor data (Wang, sec V – Input the vibration signal/”input sensor data” into a model on a computing system.) and applies physics of failure of the industrial equipment (Wang, sec IV C – A method that simulates a physical system/”applies physics of failure” of the rolling element bearing/”industrial equipment”.) to determine a prediction for remaining useful life for the industrial equipment, uncertainty in the prediction for the remaining useful life for the industrial equipment (Wang, sec V – Model the vibration signal/”input sensor data” to determine the predicted RUL along with the uncertainty.), But Wang fails to specify an explanation to the prediction for the remaining useful life for the industrial equipment. However Harding teaches an explanation to the prediction for the remaining useful life for the industrial equipment. (Harding, pg 5 para 2 - based on the simulation model, predict the failure mechanisms of the part. The failure mechanisms may include a predicted life of the part or remaining useful life, and reason for failure prediction.) Wang and Harding are analogous art because they are from the same field of endeavor. They relate to remaining useful life models. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above remaining useful life model, as taught by Wang, and incorporating the above limitations, as taught by Harding. One of ordinary skill in the art would have been motivated to do this modification in order to optimize a part maintenance plan by incorporating the above limitations, as suggested by Harding (abstract). But the combination of Wang and Harding fails to specify applying a two-tier model. However Xia teaches applying a two-tier model. (Xia, pg 3710 sec V - A two-stage DNN-based approach for RUL prediction of a bearing. In the first stage, the degradation process was divided into different health stages/classifications. In the second stage, a shallow neural network model was built and trained in each health stage of degradation to perform intermediate RUL estimation/forecast.) Wang, Harding, and Xia are analogous art because they are from the same field of endeavor. They relate to remaining useful life models. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above remaining useful life model, as taught by Wang and Harding, and incorporating the above limitations, as taught by Xia. One of ordinary skill in the art would have been motivated to do this modification in order to achieve a more accurate prediction by incorporating the above limitations, as suggested by Xia (sec V). Claim 2 The combination of Wang, Harding, and Xia teaches all the limitations of the base claims as outlined above. Xia further teaches the two-tier model comprises a forecast tier and a classification tier. (Xia, pg 3710 sec V - A two-stage DNN-based approach for RUL prediction of a bearing. In the first stage, the degradation process was divided into different health stages/classifications. In the second stage, a shallow neural network model was built and trained in each health stage of degradation to perform intermediate RUL estimation/forecast.) Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above remaining useful life model, as taught by Wang, Harding, and Xia, and incorporating the above limitations, as taught by Xia. One of ordinary skill in the art would have been motivated to do this modification in order to achieve a more accurate prediction by incorporating the above limitations, as suggested by Xia (sec V). Claim 5 The combination of Wang, Harding, and Xia teaches all the limitations of the base claims as outlined above. The combination of Wang, Harding, and Xia further teaches the industrial equipment comprises a bearing. (Wang, sec IV. A – A rolling element bearing.) This rejection also applies to claim 18. Claim 6 The combination of Wang, Harding, and Xia teaches all the limitations of the base claims as outlined above. The combination of Wang, Harding, and Xia further teaches the bearing is a rolling element bearing. (Wang, sec IV. A – A rolling element bearing.) This rejection also applies to claim 19 Claim 7 The combination of Wang, Harding, and Xia teaches all the limitations of the base claims as outlined above. The combination of Wang, Harding, and Xia further teaches the machine sensor data further comprises shaft rotation speed and loading conditions associated with the rolling element bearing. (Wang, sec VII. A – Sensor data including RPM velocity/”shaft rotation speed” and loading conditions with the roller bearings.) This rejection also applies to claim 20 Claim 8 The combination of Wang, Harding, and Xia teaches all the limitations of the base claims as outlined above. Xia further teaches the two-tier model comprises a physics-based deep learning method. (Xia, sec I, - A two-stage deep neural network (DNN) based method used to capture the physics of failure.) Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above remaining useful life model, as taught by Wang and Harding, and incorporating the above limitations, as taught by Xia. One of ordinary skill in the art would have been motivated to do this modification in order to achieve a more accurate prediction by incorporating the above limitations, as suggested by Xia (sec V). Claim 9 The combination of Wang, Harding, and Xia teaches all the limitations of the base claims as outlined above. Xia further teaches the two-tier model is an ensemble model. (Xia, sec II. A - The DNN model is constructed by stacking/ensemble all the pretrained layers.) Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above remaining useful life model, as taught by Wang and Harding, and incorporating the above limitations, as taught by Xia. One of ordinary skill in the art would have been motivated to do this modification in order to achieve a more accurate prediction by incorporating the above limitations, as suggested by Xia (sec V). Claim 11 The combination of Wang, Harding, and Xia teaches all the limitations of the base claims as outlined above. The combination of Wang, Harding, and Xia further teaches the machine sensor data comprises vibration data and the at least one sensor comprises an accelerometer. (Wang, sec VII. A – Obtaining vibration signals/”machine sensor data” by using an accelerometer sensor.) This rejection also applies to claims 21-22. Claim(s) 3-4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, “A Probabilistic Framework for Remaining Useful Life Prediction of Bearings”, 2021, IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, VOL. 70, pp 1-12 (hereinafter Wang) in view of Harding et al, Chinese Patent Num CN105741005A (hereinafter Harding) in view of Xia et al, “A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks”, June 2019, IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, VOL. 15, NO. 6, pp 3703-3710 (hereinafter Xia) as applied to claims 1-2, 5-9, 11 above, and in view of Pecht et al, “Introduction to PHM”, 2018, Prognostics and Health Management of Electronics: Fundamentals, Machine Learning, and the Internet of Things, pp 3-18 Claim 3 The combination of Wang, Harding, and Xia teaches all the limitations of the base claims as outlined above. But the combination of Wang, Harding, and Xia fails to specify the explanation to the remaining useful life for the industrial equipment is based on events occurring during operation of the industrial equipment in the industrial environment and physics-based characterizations of that type of industrial equipment failure. However Pecht teaches the explanation to the remaining useful life for the industrial equipment is based on events occurring during operation of the industrial equipment in the industrial environment (Pecht, Sec 1.3.3.1 – A reasoning algorithm to correlate/explanation the change in the precursor variable with the impending failure.) and physics-based characterizations of that type of industrial equipment failure. (Pecht, Sec 1.3.1.2 - Damage assessment was conducted using physics-based mechanical and thermomechanical damage models/”physics based characterizations of equipment failure” to determine a prognostic estimate/explanation using a combination of damage models.) Wang, Harding, Xia, and Pecht are analogous art because they are from the same field of endeavor. They relate to remaining useful life models. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above remaining useful life model, as taught by Wang, Harding, and Xia, and incorporating the above limitations, as taught by Pecht. One of ordinary skill in the art would have been motivated to do this modification in order to maintain effectiveness of equipment by incorporating the above limitations, as suggested by Pecht (sec 1.2). Claim 4 The combination of Wang, Harding, Xia, and Pecht teaches all the limitations of the base claims as outlined above. Pecht further teaches the physics-based characterizations of the industrial equipment failure are physics-based characteristic frequencies of failure. (Pecht, sec 1.3.1.2 - The extent and rate of product degradation depend upon the magnitude and duration of exposure (usage rate, frequency, and severity) to life cycle loads.) Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above remaining useful life model, as taught by Wang, Harding, Xia, and Pecht, and incorporating the above limitations, as taught by Pecht. One of ordinary skill in the art would have been motivated to do this modification in order to maintain effectiveness of equipment by incorporating the above limitations, as suggested by Pecht (sec 1.2). Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, “A Probabilistic Framework for Remaining Useful Life Prediction of Bearings”, 2021, IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, VOL. 70, pp 1-12 (hereinafter Wang) in view of Harding et al, Chinese Patent Num CN105741005A (hereinafter Harding) in view of Xia et al, “A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks”, June 2019, IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, VOL. 15, NO. 6, pp 3703-3710 (hereinafter Xia) as applied to claims 1-2, 5-9, 11 above, and in view of Lipton et al, “LEARNING TO DIAGNOSE WITH LSTM RECURRENT NEURAL NETWORKS”, Mar 2017, ICLR 2016, pp 1-10 (hereinafter Lipton) Claim 10 The combination of Wang, Harding, and Xia teaches all the limitations of the base claims as outlined above. But the combination of Wang, Harding, and Xia fails to specify the ensemble model is a two-stage Long Short-Term Memory (LSTM) model ensemble. However Lipton teaches the ensemble model is a two-stage Long Short-Term Memory (LSTM) model ensemble. (Lipton, sec 5.3 – Multilayer ensemble model that is an LSTM model.) Wang, Harding, Xia, and Lipton are analogous art because they are from the same field of endeavor. They relate to neural network models. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above neural network model, as taught by Wang, Harding, and Xia, and incorporating the above limitations, as taught by Lipton. One of ordinary skill in the art would have been motivated to do this modification in order to more effectively mine data by incorporating the above limitations, as suggested by Lipton (Abstract). Claim(s) 12-13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, “A Probabilistic Framework for Remaining Useful Life Prediction of Bearings”, 2021, IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, VOL. 70, pp 1-12 (hereinafter Wang) in view of Harding et al, Chinese Patent Num CN105741005A (hereinafter Harding) in view of Xia et al, “A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks”, June 2019, IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, VOL. 15, NO. 6, pp 3703-3710 (hereinafter Xia) as applied to claims 1-2, 5-9, 11 above, and in view of OnQ, “Developers: Building smarter edge computing solutions with smart sensors”, July 2021, Qualcomm Technologies, pp1-3 (hereinafter OnQ) Claim 12 The combination of Wang, Harding, and Xia teaches all the limitations of the base claims as outlined above. But the combination of Wang, Harding, and Xia fails to specify a sensor module comprising a housing, the at least one sensor, the computing device disposed within the housing, and the non-transitory machine readable memory disposed within the housing. However OnQ teaches a sensor module comprising a housing, the at least one sensor, the computing device disposed within the housing, and the non-transitory machine readable memory disposed within the housing. (OnQ, pg 1-3 – A smart sensor module with a housing, a computing device and memory for running software enclosed withing the housing.) Wang, Harding, Xia, and OnQ are analogous art because they are from the same field of endeavor. They relate to sensor systems. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above sensor system, as taught by Wang, Harding, and Xia, and incorporating the above limitations, as taught by OnQ. One of ordinary skill in the art would have been motivated to do this modification in order to increase overall performance and enhance power efficiency by incorporating the above limitations, as suggested by OnQ (pg 1). Claim 13 The combination of Wang, Harding, Xia, and OnQ teaches all the limitations of the base claims as outlined above. OnQ further teaches a battery disposed within the housing and wherein the sensor module is powered by the battery. (OnQ, pg 1-3 – The smart sensor module with battery enclosed in the housing.) Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above sensor system, as taught by Wang, Harding, Xia, and OnQ, and incorporating the above limitations, as taught by OnQ. One of ordinary skill in the art would have been motivated to do this modification in order to increase overall performance and enhance power efficiency by incorporating the above limitations, as suggested by OnQ (pg 1). Claim(s) 14, 18-25 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, “A Probabilistic Framework for Remaining Useful Life Prediction of Bearings”, 2021, IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, VOL. 70, pp 1-12 (hereinafter Wang) in view of Harding et al, Chinese Patent Num CN105741005A (hereinafter Harding) in view of OnQ, “Developers: Building smarter edge computing solutions with smart sensors”, July 2021, Qualcomm Technologies, pp1-3 (hereinafter OnQ). Claim 14 Wang teaches a predicting remaining useful life for industrial equipment in an industrial environment (Wang, sec IV. A – A method for predicting the remaining service life of a rolling element bearing/”industrial equipment”.), at least one sensor for sensing machine data for the industrial equipment (Wang, sec VII. A – Obtaining vibration signals/”machine sensor data” by using an accelerometer sensor connected to a processor.), wherein the processor is configured to: apply a model which receives as input sensor data comprising the machine data (Wang, sec V – Input the vibration signal/”input sensor data” into a model on a computing system.) and applies physics of failure of the industrial equipment (Wang, sec IV C – A method that simulates a physical system/”applies physics of failure” of the rolling element bearing/”industrial equipment”.) to determine a prediction for remaining useful life for the industrial equipment, uncertainty in the prediction for the remaining useful life for the industrial equipment. (Wang, sec V – Model the vibration signal/”input sensor data” to determine the predicted RUL along with the uncertainty.) But Wang fails to specify an explanation to the prediction for the remaining useful life for the industrial equipment. However Harding teaches an explanation to the prediction for the remaining useful life for the industrial equipment. (Harding, pg 5 para 2 - based on the simulation model, predict the failure mechanisms of the part. The failure mechanisms may include a predicted life of the part or remaining useful life, and reason for failure prediction.) Wang and Harding are analogous art because they are from the same field of endeavor. They relate to remaining useful life models. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above remaining useful life model, as taught by Wang, and incorporating the above limitations, as taught by Harding. One of ordinary skill in the art would have been motivated to do this modification in order to optimize a part maintenance plan by incorporating the above limitations, as suggested by Harding (abstract). But the combination of Wang and Harding fails to specify a sensor module for predicting remaining useful life for industrial equipment in an industrial environment, the sensor module comprising: a sensor housing; a processor disposed within the sensor housing; the at least one sensor operatively connected to the processor. However OnQ teaches a sensor module for predicting remaining useful life for industrial equipment in an industrial environment, the sensor module comprising: a sensor housing; a processor disposed within the sensor housing; the at least one sensor operatively connected to the processor. (OnQ, pg 1-3 – A smart sensor module with a sensor, housing, a computing/processor device and memory for running software enclosed withing the housing.) Wang, Harding, and OnQ are analogous art because they are from the same field of endeavor. They relate to sensor systems. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above sensor system, as taught by Wang and Harding, and incorporating the above limitations, as taught by OnQ. One of ordinary skill in the art would have been motivated to do this modification in order to increase overall performance and enhance power efficiency by incorporating the above limitations, as suggested by OnQ (pg 1). Claim 23 The combination of Wang, Harding, and OnQ teaches all the limitations of the base claims as outlined above. OnQ further teaches a network interface operatively connected to the processor and wherein the sensor module is configured to communicate output from the model through the network interface. (OnQ, pg 1-3 – A wireless network interface connected to the processor that communicates output data across the network.) Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above sensor system, as taught by Wang and Harding, and incorporating the above limitations, as taught by OnQ. One of ordinary skill in the art would have been motivated to do this modification in order to increase overall performance and enhance power efficiency by incorporating the above limitations, as suggested by OnQ (pg 1). Claim 24 The combination of Wang, Harding, and OnQ teaches all the limitations of the base claims as outlined above. OnQ further teaches the network interface is a wireless network interface. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above sensor system, as taught by Wang and Harding, and incorporating the above limitations, as taught by OnQ. One of ordinary skill in the art would have been motivated to do this modification in order to increase overall performance and enhance power efficiency by incorporating the above limitations, as suggested by OnQ (pg 1). Claim 25 The combination of Wang, Harding, and OnQ teaches all the limitations of the base claims as outlined above. OnQ further teaches a battery disposed within the sensor housing and wherein the sensor module is powered by the battery. (OnQ, pg 1-3 – The smart sensor module with battery enclosed in the housing.) Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above sensor system, as taught by Wang, Harding, and OnQ, and incorporating the above limitations, as taught by OnQ. One of ordinary skill in the art would have been motivated to do this modification in order to increase overall performance and enhance power efficiency by incorporating the above limitations, as suggested by OnQ (pg 1). Claim(s) 15-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, “A Probabilistic Framework for Remaining Useful Life Prediction of Bearings”, 2021, IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, VOL. 70, pp 1-12 (hereinafter Wang) in view of Harding et al, Chinese Patent Num CN105741005A (hereinafter Harding) in view of OnQ, “Developers: Building smarter edge computing solutions with smart sensors”, July 2021, Qualcomm Technologies, pp1-3 (hereinafter OnQ) as applied to claims 14, 18-25 above, and in view of Xia et al, “A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks”, June 2019, IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, VOL. 15, NO. 6, pp 3703-3710 (hereinafter Xia) Claim 15 The combination of Wang, Harding, and OnQ teaches all the limitations of the base claims as outlined above. But the combination of Wang, Harding, and OnQ fails to specify the model is a two-tier model comprising a forecast tier and a classification tier. However Xia teaches the model is a two-tier model comprising a forecast tier and a classification tier. (Xia, pg 3710 sec V - Aa two-stage DNN-based approach for RUL prediction of a bearing. In the first stage, the degradation process was divided into different health stages/classifications. In the second stage, a shallow neural network model was built and trained in each health stage of degradation to perform intermediate RUL estimation/forecast.) Wang, Harding, and Xia are analogous art because they are from the same field of endeavor. They relate to remaining useful life models. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above remaining useful life model, as taught by Wang and Harding, and incorporating the above limitations, as taught by Xia. One of ordinary skill in the art would have been motivated to do this modification in order to achieve a more accurate prediction by incorporating the above limitations, as suggested by Xia (sec V). Claim 16 The combination of Wang, Harding, and Xia teaches all the limitations of the base claims as outlined above. Xia further teaches the two-tier model comprises a physics-based deep learning method. (Xia, sec I, - A two-stage deep neural network (DNN) based method used to capture the physics of failure.) Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above remaining useful life model, as taught by Wang and Harding, and incorporating the above limitations, as taught by Xia. One of ordinary skill in the art would have been motivated to do this modification in order to achieve a more accurate prediction by incorporating the above limitations, as suggested by Xia (sec V). This rejection also applies to claim 16. Claim(s) 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, “A Probabilistic Framework for Remaining Useful Life Prediction of Bearings”, 2021, IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, VOL. 70, pp 1-12 (hereinafter Wang) in view of Harding et al, Chinese Patent Num CN105741005A (hereinafter Harding) in view of OnQ, “Developers: Building smarter edge computing solutions with smart sensors”, July 2021, Qualcomm Technologies, pp1-3 (hereinafter OnQ) as applied to claims 14, 18-25 above, and in view of Lipton et al, “LEARNING TO DIAGNOSE WITH LSTM RECURRENT NEURAL NETWORKS”, Mar 2017, ICLR 2016, pp 1-10 (hereinafter Lipton) Claim 17 The combination of Wang, Harding, and OnQ teaches all the limitations of the base claims as outlined above. But the combination of Wang, Harding, and OnQ fails to specify the ensemble model is a two-stage Long Short-Term Memory (LSTM) model ensemble. However Lipton teaches the ensemble model is a two-stage Long Short-Term Memory (LSTM) model ensemble. (Lipton, sec 5.3 – Multilayer ensemble model that is an LSTM model.) Wang, Harding, OnQ, and Lipton are analogous art because they are from the same field of endeavor. They relate to neural network models. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above neural network model, as taught by Wang, Harding, and OnQ, and incorporating the above limitations, as taught by Lipton. One of ordinary skill in the art would have been motivated to do this modification in order to more effectively mine data by incorporating the above limitations, as suggested by Lipton (Abstract). Claim(s) 26 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, “A Probabilistic Framework for Remaining Useful Life Prediction of Bearings”, 2021, IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, VOL. 70, pp 1-12 (hereinafter Wang) in view of Harding et al, Chinese Patent Num CN105741005A (hereinafter Harding) in view of Xia et al, “A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks”, June 2019, IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, VOL. 15, NO. 6, pp 3703-3710 (hereinafter Xia) in view of Lipton et al, “LEARNING TO DIAGNOSE WITH LSTM RECURRENT NEURAL NETWORKS”, Mar 2017, ICLR 2016, pp 1-10 (hereinafter Lipton) in view of OnQ, “Developers: Building smarter edge computing solutions with smart sensors”, July 2021, Qualcomm Technologies, pp1-3 (hereinafter OnQ). Claim 26 Wang teaches a method for predicting remaining useful life for industrial equipment (Wang, sec IV. A – A method for predicting the remaining service life of a rolling element bearing/”industrial equipment”.), the method comprising: monitoring machine sensor data for the industrial equipment in an industrial environment using at least one sensor, the at least one sensor comprising at least one accelerometer for sensing machine vibration data (Wang, sec VII. A – Obtaining vibration signals/”machine sensor data” by using an accelerometer sensor.); applying a model implemented by the computing device by executing a set of instructions from a non-transitory machine readable memory using a processor of the computing device, wherein the model receives as input sensor data comprising the machine sensor data (Wang, sec V – Input the vibration signal/”input sensor data” into a model on a computing system.) and applies physics of failure of the industrial equipment (Wang, sec IV C – A method that simulates a physical system/”applies physics of failure” of the rolling element bearing/”industrial equipment”.) to determine output comprising a prediction for remaining useful life for the industrial equipment, uncertainty in the prediction for the remaining useful life for the industrial equipment (Wang, sec V – Model the vibration signal/”input sensor data” to determine the predicted RUL along with the uncertainty.) But Wang fails to specify an explanation to the prediction for the remaining useful life for the industrial equipment; communicating the output from the at least one sensor to a computer having a user interface for conveying the output to a user. However Harding teaches an explanation to the prediction for the remaining useful life for the industrial equipment. (Harding, pg 5 para 2 - based on the simulation model, predict the failure mechanisms of the part. The failure mechanisms may include a predicted life of the part or remaining useful life, and reason for failure prediction.); communicating the output from the at least one sensor module to a computer having a user interface for conveying the output to a user. (Harding, pg 8 para 2 – A display screen 24 for displaying the simulation model and the distribution situation of the defect of the part.) Wang and Harding are analogous art because they are from the same field of endeavor. They relate to remaining useful life models. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above remaining useful life model, as taught by Wang, and incorporating the above limitations, as taught by Harding. One of ordinary skill in the art would have been motivated to do this modification in order to optimize a part maintenance plan by incorporating the above limitations, as suggested by Harding (abstract). But the combination of Wang and Harding fails to specify applying a two-tier model; the two-tier model comprises a physics-based deep learning method. However Xia teaches applying a two-tier model. (Xia, pg 3710 sec V - Aa two-stage DNN-based approach for RUL prediction of a bearing. In the first stage, the degradation process was divided into different health stages/classifications. In the second stage, a shallow neural network model was built and trained in each health stage of degradation to perform intermediate RUL estimation/forecast.); the two-tier model comprises a physics-based deep learning method. (Xia, sec I, - A two-stage deep neural network (DNN) based method used to capture the physics of failure.) Wang, Harding, and Xia are analogous art because they are from the same field of endeavor. They relate to remaining useful life models. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above remaining useful life model, as taught by Wang and Harding, and incorporating the above limitations, as taught by Xia. One of ordinary skill in the art would have been motivated to do this modification in order to achieve a more accurate prediction by incorporating the above limitations, as suggested by Xia (sec V). But the combination of Wang, Harding, and Xia fails to specify the two-tier model is a two-stage Long Short-Term Memory (LSTM) model ensemble. However Lipton teaches the ensemble model is a two-stage Long Short-Term Memory (LSTM) model ensemble. (Lipton, sec 5.3 – Multilayer ensemble model that is an LSTM model.) Wang, Harding, Xia, and Lipton are analogous art because they are from the same field of endeavor. They relate to neural network models. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above neural network model, as taught by Wang, Harding, and Xia, and incorporating the above limitations, as taught by Lipton. One of ordinary skill in the art would have been motivated to do this modification in order to more effectively mine data by incorporating the above limitations, as suggested by Lipton (Abstract). But the combination of Wang, Harding, Xia, and Lipton fails to specify a sensor module comprising a computing device having a non-transitory machine readable memory, at least one sensor and a processor. However OnQ teaches a sensor module comprising a computing device having a non-transitory machine readable memory, at least one sensor and a processor. (OnQ, pg 1-3 – A smart sensor module with a housing, a computing device and memory for running software enclosed withing the housing.) Wang, Harding, Xia, Lipton, and OnQ are analogous art because they are from the same field of endeavor. They relate to sensor systems. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the above sensor system, as taught by Wang, Harding, Xia, and Lipton, and incorporating the above limitations, as taught by OnQ. One of ordinary skill in the art would have been motivated to do this modification in order to increase overall performance and enhance power efficiency by incorporating the above limitations, as suggested by OnQ (pg 1). Citation of Pertinent Prior Art The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Iwatsubo et al, US Patent Pub US 20070277613 A1 relates to claims regarding a method for assessing the remaining service life of a rolling bearing, and acquiring baseline data acquisition means for obtaining vibration signals by using an accelerometer. Kalgren et al, US Patent Pub US 20120191384 A1 prognostic health management, vibration measurement, generating performance models, and determining remaining useful life. Hotait et al, "Intelligent Online Monitoring of Rolling Bearing: Diagnosis and Prognosis", 2021, Entropy, pp 1-15 relates to claims regarding a method to predict the Remaining Useful Life (RUL) of rolling bearings based on Long Short Term Memory (LSTM), vibration sensors, and bearing speed and loading. Li et al, "An Improved Exponential Model for Predicting Remaining Useful Life of Rolling Element Bearings", 2015, IEEE, pp 7762-7772 relates to claims regarding developing a model in RUL prediction of rolling element bearings, vibration measurement. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to DAVID E OGG whose telephone number is (469) 295-9163. The examiner can normally be reached on Mon - Thurs 7:30 am - 5:00 pm CT. 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, 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 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. /DAVID EARL OGG/ Primary Examiner, Art Unit 2119
Read full office action

Prosecution Timeline

Dec 14, 2023
Application Filed
Mar 17, 2026
Non-Final Rejection — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12596339
PRODUCTION MANAGEMENT DEVICE, PRODUCTION MANAGEMENT SYSTEM, PRODUCTION MANAGEMENT METHOD, AND STORAGE MEDIUM
2y 5m to grant Granted Apr 07, 2026
Patent 12591217
METHOD AND SYSTEM FOR PROVIDING RECOMMENDATIONS CONCERNING A CONFIGURATION PROCESS
2y 5m to grant Granted Mar 31, 2026
Patent 12572134
I/O Server Services for Selecting and Utilizing Active Controller Outputs from Containerized Controller Services in a Process Control Environment
2y 5m to grant Granted Mar 10, 2026
Patent 12547153
METHOD, CONTROL UNIT, MEASUREMENT SYSTEM, COMPUTER PROGRAM PRODUCT
2y 5m to grant Granted Feb 10, 2026
Patent 12544834
AGENT DROPLET DEPOSITION DENSITY DETERMINATIONS FOR POROUS ARTICLES
2y 5m to grant Granted Feb 10, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

1-2
Expected OA Rounds
83%
Grant Probability
95%
With Interview (+12.1%)
2y 8m
Median Time to Grant
Low
PTA Risk
Based on 290 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month