Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
This Office Action is sent in response to Application’s Communication received on 04/18/2023 for application number 18/302393. The Office hereby acknowledges receipt of the following and placed of record in file: Specification, Drawing, Abstract, Oath/Declaration, and Claims.
Claims (1-10), (11-19) and 20 are presented for examination.
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.
Claims 1-8 and 11-17 recite acronym describing GAN, SDD, WDCGAN-GP, DCNN, DGCG and GLU without defining the acronym. For the purpose of examination, the acronym will fall within the scope of GAN, SDD, WDCGAN-GP, DCNN, DGCG and GLU.
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 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.
Claims 1-3 and 11-13 are rejected under AIA 35 U.S.C. 103(a) as being unpatentable over Zheng et al. US Patent Application Publication US 20210279596 A1 (hereinafter Zheng) in view of Hao Lu et al. GAN-LSTM Predictor for Failure Prognostics of Rolling Element Bearings, 2021 (hereinafter Lu) and further in view of Hu Jong Wan. Foreign Application Publication KR 102600548 B1 (hereinafter Wan) and further in view of Wang et al. US 20230104028 A1 (hereinafter Wang) and further in view of Cella et al. US Patent Application Publication US 20190171187 A1 (hereinafter Cella).
Regarding claim 1, Zheng teaches A method for automatically diagnosing a condition of at least one structure, the method comprising the steps of: receiving, via at least one sensor communicatively coupled to a computing device, at least one actual sensor response from at least one structure, wherein the at least one sensor…with the at least one structure, whereby the at least one actual sensor response comprises at least one actual damaged scenario, at least one actual undamaged scenario, or both ([0006-0008], [0021], [0025-0028], [0037], [0055] wherein Zheng describes a method for monitoring sensor data that may include samples with failure or non-failure probability. Wherein the method involves generating training and deploying a failure prediction model that involves generated sensor data and real sensor data to a network integrated into a generative adversarial network (GAN). Wherein the real sensor data and the generated sensor data may include scenarios of failure or non-failure scenarios)
Zheng does not teach sensor is in mechanical communication.
However in analogous art of structural damage diagnostics, Lu teaches sensor is in mechanical communication (Abstract, page. 1, paragraph 1 wherein Lu teaches an approach for detecting failure prognostics of machine components and predicting the remaining useful of mechanical components and industrial system prior failures. Wherein the approach employs machine learning techniques to capture the bearing degradation pattern without making any assumptions on the underlying damage mechanisms) comparing, via the processor of the computing device, the at least one trained prediction dataset with at least one unseen sensor response from the at least one structure (FIG. 3, page. 2, paragraph 9, page. 3, paragraph 5, page. 4, page. 6, paragraphs 3, 5, page. 7, paragraph 2 wherein Lu describes the LSTM predictor that is trained using both the real training data and the generated data obtained from the generator network, wherein the predictor’s performance is enhanced by augmenting real training data with synthetic data generated by a GAN. To obtain a complete forecast up to the failure threshold, the GAN-LSTM predictor is repeatedly evaluated by marching in time, treating predicted values as new data points. Wherein Lu describes using the trained generated data with the real data that represents the sensors response which implies comparing both data to assess the damage) and automatically predicting, via the processor of the computing device, the condition of the at least one structure on a display device associated with the computing device by (page. 2, paragraph 1, wherein Lu enhances the LSTM model’s cognitive ability in estimating and predicting degradation, a dynamic differential feature extraction method that is utilized that enabled capturing the changes of features under different operating conditions).
It would have been obvious to a person in the ordinary skill in the art before the effective filing date of the claimed invention to combine Zheng with Lu by incorporating the method of sensor is in mechanical communication; comparing, via the processor of the computing device, the at least one trained prediction dataset with at least one unseen sensor response from the at least one structure of Lu into the method of receiving, via at least one sensor communicatively coupled to a computing device, at least one actual sensor response from at least one structure, wherein the at least one sensor…with the at least one structure, whereby the at least one actual sensor response comprises at least one actual damaged scenario, at least one actual undamaged scenario, or both of Zheng for the purpose of incorporating a GAN-based LSTM framework for bearing degradation data augmentation to enhance the model’s prediction accuracy and robustness in forecasting future degradation trajectories. (Lu: page. 2, paragraph 7).
Zheng as modified by Lu teach augmenting, via at least one GAN architecture of the processor, the at least one actual sensor response with at least one synthetic sensor response, wherein the at least one synthetic sensor response comprises at least one synthetic damaged scenario, at least one synthetic undamaged scenario, or both, whereby the at least one actual sensor response, at least one synthetic sensor response, or both are compiled into at least one augmented sensorial dataset (page. 3, paragraph 5, wherein Lu teaches augmenting real training data with synthetic data generated by a GAN to obtain a complete forecast up to the failure threshold, wherein a GAN-LSTM predictor is repeatedly evaluated by marching in time, treating predicted values as new data points).
Zheng teaches training…at least one prediction dataset based on the at least one augmented sensorial dataset ([0006-0008], [0028], [0032], [0037] wherein Zheng describes a method for using failure prediction model, wherein the method involves providing generated sensor data and real sensor data to GAN as prediction dataset).
Zheng does not teach via at least one DL-based SDD architecture of the processor.
However in analogous art of structural damage diagnostics, Wan teaches via at least one DL-based SDD architecture of the processor (FIG. 3, page. 2, paragraph 3, wherein Wan incorporates a technology for structural damage and diagnostic).
It would have been obvious to a person in the ordinary skill in the art before the effective filing date of the claimed invention to combine Zheng with Wan by incorporating the method of via at least one DL-based SDD architecture of the processor of Wan into the method of receiving, via at least one sensor communicatively coupled to a computing device, at least one actual sensor response from at least one structure, wherein the at least one sensor…with the at least one structure, whereby the at least one actual sensor response comprises at least one actual damaged scenario, at least one actual undamaged scenario, or both of Zheng for the purpose of incorporating structural health monitoring (SHM) for observing structural damage to structures using non-destructive texting that overserved by sensors and transmitted to SHM system, wherein the SHM specifies the extent and location of damage and provide in real time to enable proactive response (Wan: page. 2, paragraph 4).
Zheng does not teach based on determination that the at least one unseen sensor response from the at least one sensor matches the at least one actual damaged scenario, at least one synthetic damaged scenario, or both of the at least one trained prediction dataset, transmitting a notification indicative of a damaged condition.
However in analogous art of structural damage diagnostics, Wang teaches based on determination that the at least one unseen sensor response from the at least one sensor matches the at least one actual damaged scenario, at least one synthetic damaged scenario, or both of the at least one trained prediction dataset, transmitting a notification indicative of a damaged condition ([0004], [0009-0010], [0016-0017], [0034], [0036], [0041], [0047], [0062] wherein Wang describes proposed failure prediction system that is valuable in a wide range of industries where generating warnings for incoming failures are essential for the business).
It would have been obvious to a person in the ordinary skill in the art before the effective filing date of the claimed invention to combine Zheng with Wang by incorporating the method of based on determination that the at least one unseen sensor response from the at least one sensor matches the at least one actual damaged scenario, at least one synthetic damaged scenario, or both of the at least one trained prediction dataset, transmitting a notification indicative of a damaged condition of Wang into the method of receiving, via at least one sensor communicatively coupled to a computing device, at least one actual sensor response from at least one structure, wherein the at least one sensor…with the at least one structure, whereby the at least one actual sensor response comprises at least one actual damaged scenario, at least one actual undamaged scenario, or both of Zheng for the purpose of incorporating systems and methods that involve executing a functional generator configured to generate multivariate continuous sensor curves from training with arbitrary multivariate sensor data with irregular timestamps received from one or more apparatuses; executing a functional discriminator to discriminate the generated multivariate continuous sensor curve from the arbitrary multivariate sensor data; and for the functional discriminator discriminating the generated multivariate continuous sensor curve from the arbitrary multivariate sensor data with irregular timestamps, providing feedback to the functional generator to retrain the functional generator (Wang: Abstract).
Zheng as modified by Lu teach and based on determination that the at least one unseen sensor response from the at least one sensor does not match the at least one actual undamaged scenario, at least one synthetic undamaged scenario, or both of the at least one trained prediction dataset (page. 3, paragraph 5, wherein Lu teaches augmenting real training data with synthetic data generated by a GAN to obtain a complete forecast up to the failure threshold, wherein a GAN-LSTM predictor is repeatedly evaluated by marching in time, treating predicted values as new data points), (FIG. 3, page. 2, paragraph 9, page. 3, paragraph 5, page. 4, page. 6, paragraphs 3, 5, page. 7, paragraph 2 wherein Lu describes the LSTM predictor that is trained using both the real training data and the generated data obtained from the generator network, wherein the predictor’s performance is enhanced by augmenting real training data with synthetic data generated by a GAN. To obtain a complete forecast up to the failure threshold, the GAN-LSTM predictor is repeatedly evaluated by marching in time, treating predicted values as new data points. Wherein Lu describes using the trained generated data with the real data that represents the sensors response which implies comparing both data to assess the damage).
However in analogous art of structural damage diagnostics, Zheng does not teach transmitting a notification indicative of an undamaged condition.
Cella teaches transmitting a notification indicative of an undamaged condition ([1723] wherein Cella transmits alerts of the correctness of the sensor package).
It would have been obvious to a person in the ordinary skill in the art before the effective filing date of the claimed invention to combine Zheng with Cella by incorporating the method of transmitting a notification indicative of an undamaged condition of Cella into the method of receiving, via at least one sensor communicatively coupled to a computing device, at least one actual sensor response from at least one structure, wherein the at least one sensor…with the at least one structure, whereby the at least one actual sensor response comprises at least one actual damaged scenario, at least one actual undamaged scenario, or both of Zheng for the purpose of incorporating a pattern recognition circuit that can readily determine the most important set of sensors to effectively predict patterns and thus system conditions requiring a response (Cella: [1539]).
Regarding claim 2, Zheng as modified by Lu, Wan, Wang and Cella teaches wherein the at least one GAN architecture of the processor comprises a WDCGAN-GP architecture, a CycleWDCGAN-GP architecture, or both ([0010] wherein Wang describes Generative Adversarial Network (GAN) models for time series data that includes C-RNN-GAN, RC-GAN, TimeGAN, T-CGAN).
Regarding claim 3, Zheng as modified by Lu, Wan, Wang and Cella teaches wherein the at least one GAN architecture is configured to output at least one datapoint within the at least one augmented sensorial dataset in one-dimension (hereinafter “1D”) (FIGS. 2, 5, [0004], [0028], [0037], [0055] wherein Zheng outputs generated samples as illustrated in FIGS. 2, 5, wherein the output is based on combining real sensor data with the generated sensor data), (Abstract, page. 2, paragraph 7, page. 3, paragraphs 5-8 wherein Lu augments real training data with synthetic data generated by a GAN and obtains a complete forecast up to the failure threshold, wherein a GAN-LSTM predictor is repeatedly evaluated by marching in time, treating predicted values as new data points).
Regarding claim 11, Zheng teaches a structure diagnosis optimization system for automatically predicting a condition of at least one structure, the structure diagnosis optimization system comprising ([0006-0008], [0021], [0025-0028], [0037], [0055] wherein Zheng describes a method for monitoring sensor data that may include samples with failure or non-failure probability. Wherein the method involves generating training and deploying a failure prediction model that involves generated sensor data and real sensor data to a network integrated into a generative adversarial network (GAN). Wherein the real sensor data and the generated sensor data may include scenarios of failure or non-failure scenarios) a computing device having a processor (FIGS. 6-7, [0016], [0022], [0046]) and a non-transitory computer-readable medium operably coupled to the processor, the computer-readable medium having computer-readable instructions stored thereon that, when executed by the processor, cause the structure diagnosis optimization system to automatically predict the condition of the at least one civil structure by executing instructions comprising ([0062]). Claim 11 is similar in scope to claim 1 therefore the claim is rejected under similar rationale.
Regarding claim 13, the claim is similar in scope to claim 3 therefore the claim is rejected under similar rationale.
Regarding claim 20, the claim is similar in scope to claim 1 therefore the claim is rejected under similar rationale.
Claims 4-6 and 14-15 are rejected under AIA 35 U.S.C. 103(a) as being unpatentable over Zheng et al. US Patent Application Publication US 20210279596 A1 (hereinafter Zheng) in view of Hao Lu et al. GAN-LSTM Predictor for Failure Prognostics of Rolling Element Bearings, 2021 (hereinafter Lu) and further in view of Hu Jong Wan. Foreign Application Publication KR 102600548 B1 (hereinafter Wan) and further in view of Wang et al. US 20230104028 A1 (hereinafter Wang) and further in view of Cella et al. US Patent Application Publication US 20190171187 A1 (hereinafter Cella) and further in view of Jian Zhou et al. Foreign Application Publication CN 111326170 B (hereinafter Zhou).
Regarding claim 4, Zheng as modified by Lu, Wan, Wang and Cella do not teach wherein the at least one GAN architecture may further comprise an algorithm selected from a group consisting of a GLU, at least one skip-connection, the Mish activation function, and a combination of thereof.
However in analogous art of structural damage diagnostics, Zhou teaches wherein the at least one GAN architecture may further comprise an algorithm selected from a group consisting of a GLU, at least one skip-connection, the Mish activation function, and a combination of thereof (Abstract, page. 4, paragraph 4, page. 8, paragraph 11, page 9, paragraph 4, wherein Zhou incorporates skip connection and describes MISH activation function that allows the network to have gradient flow for training the deeper network).
It would have been obvious to a person in the ordinary skill in the art before the effective filing date of the claimed invention to combine Zhou with Zheng, Lu, Wan, Wang and Cella by incorporating the method of transmitting a notification indicative of an undamaged condition of Zhou into the method of receiving, via at least one sensor communicatively coupled to a computing device, at least one actual sensor response from at least one structure, wherein the at least one sensor…with the at least one structure, whereby the at least one actual sensor response comprises at least one actual damaged scenario, at least one actual undamaged scenario, or both of Zheng, Lu, Wan, Wang and Cella for the purpose of improving the stability of the model training process (Zhou: page. 8, paragraph 11).
Regarding claim 5, Zheng as modified by Lu, Wan, Wang, Cella and Zhou teaches wherein the at least one DL-based SDD architecture comprises at least one DCNN architecture (page. 7, paragraph 7-11, page. 8, paragraph 1 wherein Zhou describes DCNN architecture).
Regarding claim 6, Zheng as modified by Lu, Wan, Wang, Cella and Zhou teaches wherein the at least one DL-based SDD architecture is configured to output at least one datapoint within the at least one trained prediction dataset in 1D (page. 1, paragraph 6 wherein Lu employs machine learning techniques to capture the bearing degradation pattern and underlying damage mechanisms. Wherein GAN-LSTM predictor is used to predict the trajectory of the degradation feature, wherein an input sequence of length is fed into the trained LSTM predictor with the time step of the last element marked as _CDEFGHIJKD. Each next-step prediction value is used as a new data point, and the prediction is performed until the predicted value crosses the predefined threshold of EOL and marking the time).
Claim 14 is similar in scope to claim 5 therefore the claim is rejected under similar rationale.
Claim 15 is similar in scope to claim 6 therefore the claim is rejected under similar rationale.
Claims 7-10 and 16-19 are rejected under AIA 35 U.S.C. 103(a) as being unpatentable over Zheng et al. US Patent Application Publication US 20210279596 A1 (hereinafter Zheng) in view of Hao Lu et al. GAN-LSTM Predictor for Failure Prognostics of Rolling Element Bearings, 2021 (hereinafter Lu) and further in view of Hu Jong Wan. Foreign Application Publication KR 102600548 B1 (hereinafter Wan) and further in view of Wang et al. US 20230104028 A1 (hereinafter Wang) and further in view of Cella et al. US Patent Application Publication US 20190171187 A1 (hereinafter Cella) and further in view of D’Mello Yannick et al. Foreign Application Publication CA 3181091 A (hereinafter Yannick).
Regarding claim 7, Zheng as modified by Lu, Wan, Wang and Cella does not teach wherein the processor of the computing device further comprises a DGCG architecture.
However in analogous art of structural damage diagnostics, Yannick teaches teach wherein the processor of the computing device further comprises a DGCG architecture ([0519] wherein Yannick teaches DGCG).
It would have been obvious to a person in the ordinary skill in the art before the effective filing date of the claimed invention to combine Yannick with Zheng, Lu, Wan, Wang and Cella by incorporating the method of wherein the processor of the computing device further comprises a DGCG architecture of Yannick into the method of receiving, via at least one sensor communicatively coupled to a computing device, at least one actual sensor response from at least one structure, wherein the at least one sensor…with the at least one structure, whereby the at least one actual sensor response comprises at least one actual damaged scenario, at least one actual undamaged scenario, or both of Zheng, Lu, Wan, Wang and Cella for the purpose of extracting sensor signals as vectorial projections onto coordinates axes (Yannick: [0518]).
Regarding claim 8, Zheng as modified by Lu, Wan, Wang, Cella and Yannick teaches the step of, after training the at least one prediction dataset, learning, via the DGCG architecture of the processor, at least one domain-invariant representation of at least one domain of the at least one structure, wherein the at least one domain comprises the at least one scenario of the at least one actual sensor response, at least one synthetic response, or both of the at least one structure, whereby the at least one scenario comprises at least one actual, synthetic, or both damaged scenario, at least one actual, synthetic, or both undamaged scenario, or both (FIGS. 2, 5, [0004], [0028], [0037], [0055] wherein Zheng outputs generated samples as illustrated in FIGS. 2, 5, wherein the output is based on combining real sensor data with the generated sensor data), (Abstract, page. 2, paragraph 7, page. 3, paragraphs 5-8 wherein Lu augments real training data with synthetic data generated by a GAN and obtains a complete forecast up to the failure threshold, wherein a GAN-LSTM predictor is repeatedly evaluated by marching in time, treating predicted values as new data points), ([0004], [0009-0010] wherein Wang describes a technique for domain to design with generative Adversarial Network (GAN) models for time series including C-RNN-GAN, RC-GAN, TimeGAN, T-CGAN. These GAN architectures are deployed to study the statistical characteristics of sensor data prior to actual failures and synthesize more failure data instances that follow the same underlying dynamics).
Regarding claim 9, Zheng as modified by Lu, Wan, Wang, Cella and Yannick teaches the step of, after learning the domain-invariant representation, applying, via the processor of the computing device, the domain-invariant representation to at least one alternative structure ([0004], [0009-0010] wherein Wang describes a technique for domain to design with generative Adversarial Network (GAN) models for time series including C-RNN-GAN, RC-GAN, TimeGAN, T-CGAN. These GAN architectures are deployed to study the statistical characteristics of sensor data prior to actual failures and synthesize more failure data instances that follow the same underlying dynamics).
Regarding claim 10, Zheng as modified by Lu, Wan, Wang, Cella and Yannick teaches the step of, after applying the domain-invariant representation to at least one alternative structure, automatically predicting, via the processor of the computing device, a condition of the at least one alternative structure on a display device associated with the computing device by (page. 2, paragraph 1, wherein Lu enhances the LSTM model’s cognitive ability in estimating and predicting degradation, a dynamic differential feature extraction method that is utilized that enabled capturing the changes of features under different operating conditions) based on determination that at least one alternative domain source of the alternative structure matches the at least one domain source comprising at least one damaged scenario of the at least one structure, transmitting a notification indicative of a damaged condition ([0004], [0009-0010], [0016-0017], [0034], [0036], [0041], [0047], [0062] wherein Wang describes proposed failure prediction system that is valuable in a wide range of industries where generating warnings for incoming failures are essential for the business) and based on determination that at least one alternative domain source of the alternative structure does not match the at least one domain source comprising at least one damaged scenario of the at least one structure, transmitting a notification indicative of an undamaged condition (page. 3, paragraph 5, wherein Lu teaches augmenting real training data with synthetic data generated by a GAN to obtain a complete forecast up to the failure threshold, wherein a GAN-LSTM predictor is repeatedly evaluated by marching in time, treating predicted values as new data points), (FIG. 3, page. 2, paragraph 9, page. 3, paragraph 5, page. 4, page. 6, paragraphs 3, 5, page. 7, paragraph 2 wherein Lu describes the LSTM predictor that is trained using both the real training data and the generated data obtained from the generator network, wherein the predictor’s performance is enhanced by augmenting real training data with synthetic data generated by a GAN. To obtain a complete forecast up to the failure threshold, the GAN-LSTM predictor is repeatedly evaluated by marching in time, treating predicted values as new data points. Wherein Lu describes using the trained generated data with the real data that represents the sensors response which implies comparing both data to assess the damage), ([0004], [0009-0010], [0016-0017], [0034], [0036], [0041], [0047], [0062] wherein Wang describes proposed failure prediction system that is valuable in a wide range of industries where generating warnings for incoming failures are essential for the business).
Claim 16 is similar in scope to claim 7 therefore the claim is rejected under similar rationale.
Claim 17 is similar in scope to claim 8 therefore the claim is rejected under similar rationale.
Claim 18 is similar in scope to claim 9 therefore the claim is rejected under similar rationale.
Claim 19 is similar in scope to claim 10 therefore the claim is rejected under similar rationale.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HASSAN MRABI whose telephone number is (571)272-8875. The examiner can normally be reached on Monday-Friday, 7:30am-5pm. Alt, Friday, EST.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Viker Lamardo can be reached on 571-270-5871. 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.
/HASSAN MRABI/Examiner, Art Unit 2144