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 .
Response to Amendment
This office action is in response to applicant’s amendment received on 07/20/2026.
Claims 30, 31, 39, 40, 45, and 46 have been amended.
Claims 1-29 have been cancelled.
Claim 50 has been added.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 30-31, 33-34, 36-40, 42-43, 45-46, and 48-50 is/are rejected under 35 U.S.C. 103 as being unpatentable over Shao et al. ("A Deep Learning Approach for Fault Diagnosis of Induction Motors in Manufacturing") in view of Chen et al. (CN 107121926 A).
Regarding claims 30, 39, and 45, Shao et al. disclose a method, comprising:
obtaining, with at least one processor, sensor data associated with operation of industrial equipment (a least implicitly disclosed in the Abstract and the Introduction: sensor data from a motor is acquired and processed);
inputting, with at least one processor, the sensor data to an ensemble trained machine learning models (pages 1348-1350: RBM model and DBN model), wherein the ensemble of trained machine learning models comprises a physics based feature extraction model that predicts a first operating condition (see pages 1349-1350, page 1349, left column: A RBM model contains two layers: One layer is the input layer which is also called visible layer, and the other layer is the output layer which also called hidden layer. RBM can be represented as a bipartite undirected graphical model. All the visible units of the RBM are fully connected to hidden units, while units within one layer do not have any connection between each other and 1350 right column: Therefore, in this study the vibration signals are transformed from time domain to frequency domain using FFT, and the frequency distribution of each signal is used as input of the RBM architecture for train RBM model. The feature RMD model is considered to equate the feature "physic based feature extraction model". This interpretation is in line with §147 of the present application) and a deep learning based automatic feature extraction model that predicts a second operating condition (see Fig.5: the block "Trained DBN" represents a deep learning network architecture which according to page 1348, right column, lines 19-21 can extract "features"); and predicting, with the at least one processor, operating conditions associated with operation of the industrial equipment using the trained machine learning models (see page 1351, Fig. 5 and the left column: Classification process is then followed to predict the fault category ).
Shao et al. fail to disclose predicting, with the at least one processor, operating conditions associated with operation of the industrial equipment using multiple predictions from the ensemble of trained machine learning models.
Chen et al. teaches predicting, with the at least one processor, operating conditions associated with operation of the industrial equipment using multiple predictions from the ensemble of trained machine learning models (abstract: an industrial robot reliability modelling method based on deep learning, comprising the following steps: constructing deep neural network DNN by limiting Boltzmann machine RBM; training RBM and DNN by using contrast dispersion fast learning algorithm, and evaluating the training result; inputting the accelerated degradation original data of the evaluation object industrial robot, constructing the acceleration degradation model, predicting the expected working life and reliability under the normal working condition). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claim invention to incorporate predicting, with the at least one processor, operating conditions associated with operation of the industrial equipment using multiple predictions from the ensemble of trained machine learning models of Chen et al. with the system and method of Shao et al. for the purposes of providing an improved industrial robot reliability modelling method based on deep learning (Chen et al., abstract).
Regarding claims 31, 40, and 46, Shao et al. disclose wherein the physics based feature extraction model is built using supervised learning with labeled data comprising labels that correspond to the operating conditions, the labeled data comprising sensor data from a sensor hub (p.1350, right column, lines 14-18).
Regarding claims 33, 42, and 48, Shao et al. disclose the deep learning based automatic feature extraction model is trained using unsupervised learning with thresholds calculated from signal distributions in additional sensor data, wherein the thresholds are associated with the operating conditions (page 1251, left column: "The unsupervised..”) .
Regarding claim 34, 43, and 49, Shao et al. disclose the deep learning based automatic feature extraction model is trained using unsupervised learning with labeled data comprising labels that correspond to a normal operating condition, the labeled data comprising additional sensor data and additional temperature data (page 1251, left column: "The unsupervised..”).
Regarding claim 36, “wherein the trained machine learning model is actively trained based on unlabeled input data by identifying patterns in the unlabeled input data, and predicting the operating conditions is based on, at least in part, the identified patterns“ is considered to be a well-known procedure.
Regarding claim 37, “obtaining additional sensor data, additional temperature data, operational parameters, or a combination thereof from sensor hubs at two or more time intervals, wherein the additional sensor data is associated with the industrial equipment, and wherein the two or more time intervals include at least a first time interval and a second time interval, the first time interval spanning a first amount of time during a given day, and the second time interval spanning a second amount of time during the given day, the second amount of time being shorter than the first amount of time and being separated from the first amount of time during the given day; labeling the additional sensor data, the additional temperature data, and the operational parameters as corresponding to at least one operating condition; and training the machine learning model using a training dataset comprising the labeled additional sensor data, the labeled additional temperature data, and the labeled operating parameters” is considered to represent obvious design options the skilled person would choose under the dictate of circumstances.
Regarding claim 38, “training the machine learning model using additional sensor data, additional temperature data, infrared heat maps of a product being produced by the industrial equipment, images of the product being produced by the industrial equipment, or any combinations thereof” is considered to represent obvious design options the skilled person would choose under the dictate of circumstances.
Regarding claim 50, Chen et al. disclose wherein a voting scheme is applied to the multiple predictions from the ensemble of machine learning models to determine a final prediction of operating conditions associated with industrial equipment (Chen et al., page 6, last paragraph and page 7 first paragraph: CD learning training algorithm, greatly improving the learning efficiency of the prediction model. firstly discussing the single layer RBM model construction, forming DNN by single layer RBM stack, using CD fast learning algorithm to train RBM layer by layer, finally obtaining the most optimized prediction model parameter and result output).
Claim(s) 32, 41, and 47 is/are rejected under 35 U.S.C. 103 as being unpatentable over Shao et al. ("A Deep Learning Approach for Fault Diagnosis of Induction Motors in Manufacturing") in view of Chen et al. (CN 107121926 A) as applied to claim 30 above, and further in view of Nadeem et al.("Outlier Detection in Sensor Data using Ensemble Learning").
Regarding claim 32 , 41, and 47, the combination of Shao et al. and Chen et al. fail to disclose re-shaping the sensor data into intermediate buckets to form bucketed data; dividing the bucketed data into sub-sample windows; extracting features from the sub-sampled windows; and predicting the operating conditions for each respective sub-sample window according to the extracted features, wherein an operating condition associated with the intermediate buckets is determined according to a number of predictions associated with the sub-sample windows.
Nadeem et al. teach re-shaping the sensor data into intermediate buckets to form bucketed data; dividing the bucketed data into sub-sample windows; extracting features from the sub-sampled windows; and predicting the operating conditions for each respective sub-sample window according to the extracted features, wherein an operating condition associated with the intermediate buckets is determined according to a number of predictions associated with the sub-sample windows (abstract). Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of Nadeem et al. with the teaching of Shao et al. in view of Chen et al. in order to provide outlier detection in sensor data using ensemble learning.
Claim(s) 35 and 44 is/are rejected under 35 U.S.C. 103 as being unpatentable over Shao et al. ("A Deep Learning Approach for Fault Diagnosis of Induction Motors in Manufacturing") in view of Chen et al. (CN 107121926 A) as applied to claim 30 above, and further in view of Umer et al. (""Machine Learning-based Real-Time Sensor Drift Fault Detection using Raspberry Pi ").
Regarding claims 35 and 44, the combination of Shao et al. and Chen et al. fail to disclose detecting a drift from a normal operating condition, wherein the trained machine learning model is actively trained in response to determining a cause of the drift is a modified configuration of the industrial equipment, wherein active training uses the determined cause of the drift.
Umer et al. teach detecting a drift from a normal operating condition, wherein the trained machine learning model is actively trained in response to determining a cause of the drift is a modified configuration of the industrial equipment, wherein active training uses the determined cause of the drift (abstract). Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of Umer et al. with the teaching of Shao et al. in view of Chen et al. in order to provide machine learning-based real-time sensor drift fault detection.
Response to Arguments
Applicant's arguments filed 07/20/2026 have been fully considered but they are not persuasive.
-Applicant argues that the actual claims recite “an integrated computing and sensor environment where sensor data is input into an ensemble of trained machine learning models, specifically combining a physics-based feature extraction model predicting a first operating condition and a deep learning automatic feature extraction model predicting a second operating condition to accurately predict physical machinery asset states”. The subject matter of claims 30, 39, and 45 provides multiple technical improvements overcoming deficiencies of prior approaches. As such, patent-eligibility of the pending claims is readily apparent from overwhelming precedential Federal Circuit case law. That is, because the subject matter of the claims provides technical improvements, the subject matter is not abstract, and/or there is more than any abstract idea alone.
Response: The examiner agrees, therefore the rejection under 101 of claims 30-49 has been withdrawn.
-Applicant argues that the prior art does not teach, “a physics based feature extraction model that predicts a first operating condition” as cited in claim 1.
Response: The examiner respectfully disagrees. Shao et al. disclose a physics based feature extraction model that predicts a first operating condition (see pages 1349-1350, page 1349, left column: A RBM model contains two layers: One layer is the input layer which is also called visible layer, and the other layer is the output layer which also called hidden layer. RBM can be represented as a bipartite undirected graphical model. All the visible units of the RBM are fully connected to hidden units, while units within one layer do not have any connection between each other and 1350 right column: Therefore, in this study the vibration signals are transformed from time domain to frequency domain using FFT, and the frequency distribution of each signal is used as input of the RBM architecture for train RBM model. The feature RMD model is considered to equate the feature "physic based feature extraction model". This interpretation is in line with §147 of the present application).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOHN H LE whose telephone number is (571)272-2275. The examiner can normally be reached on Monday-Friday from 7:00am – 3:30pm ET.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Shelby A. Turner can be reached on (571) 272-6334. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/JOHN H LE/Primary Examiner, Art Unit 2857
Prosecution Insights