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
Applicant' s amendment and response filed 4/6/2026 has been entered and made record. This application contains 16 pending claims.
Claims 1, 4, 7-8, 11, and 16-17 have been amended.
Claims 3 and 10 have been cancelled.
Response to Arguments
Applicant’s arguments filed 4/6/2026 regarding claims objections in claims 1, 8, and 17 have been fully considered and are persuasive. Claims 1, 8, and 17 have been amended, and the amended claims limitations overcome the claims objections. Therefore, claims objections in claims 1, 8, and 17 have been withdrawn.
Applicant’s arguments filed 4/6/2026 regarding claims rejections under 35 U.S.C. 101 in claim 1-18 have been fully considered but they are not persuasive.
The applicant argues on pages 7-9 of the remark filed on 4/6/2026 that “… The 101 rejection hinges on the assertion that "processing the vibration data into processed data" and then inputting it into a CNN is generic, amounting to "insignificant extra-solution activity." Applicants respectfully submit that amended claim 1 fully satisfies 35 U.S.C. §101 because it is directed to a specific, inventive application of data processing which improves the technology or the functioning of the computer/CNN itself, which goes far beyond a mere abstract idea. … .”
The Examiner respectfully disagrees applicant’s argument. The steps of “forming continuous wavelet coefficient matrices (CWCM) from the vibration data and monitoring operating condition information of the target bearing”; “creating fused bearing information maps comprising an energy spectrum of the CWCM and the operating condition information”; “diagnose an occurrence of a fault in the target bearing based on the fused bearing information maps”; and “when a fault is diagnosed by the STP fault detection CNN, triggering operation of a machine-learned fault model-selection convolutional neural network (CNN) trained” are mathematical concepts, therefore, they are considered to be an abstract idea. Thus, the claims are directed to an abstract idea.
The applicant argues on pages 9-11 of the remark filed that “… When it comes to requisite consideration of Step 2A Prong 2 - Integration into a Practical Application, it is clear that amended claim 1 in any event recasts any perceived abstract idea into a specific, tangible, and inventive solution by utilizing a specialized arrangement that improves the functioning of a computer or improves another technology or technical field. In particular, amended claim 1 affirmatively recites various features in furtherance of the practical application achieved. … The claimed combination of creating a specialized data structure (the fused information maps) to trigger a novel dual-CNN architecture provides a specific technical solution that improves the functioning of the machine learning models and the technological field of bearing fault prognosis. … Furthermore, the PTO has already acknowledged on the record that the prior art fails to teach the specific dual-CNN triggering mechanism recited in the claims. When such novel, allowable architecture is combined with the specific data transformation steps which are the fused information maps, it constitutes an ordered combination that integrates the judicial exception into a practical application.”
The Examiner respectfully disagrees applicant’s argument. Practical application can be demonstrated by additional elements that are sufficient to integrate the judicial exception into a practical application. The additional element “monitoring a target bearing to obtain vibration data from the target bearing” is considered a necessary data gathering and thus, not sufficient to integrate the abstract idea into a practical application. As recited in MPEP section 2106.05(g), necessary data gathering (i.e., obtain vibration data) is considered extra solution activity in light of Mayo, 566 U.S. at 79, 101 USPQ2d at 1968; OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015).
The additional elements “inputting the fused bearing information maps into a machine-learned start-to-prognosis (STP) fault detection convolutional neural network (CNN) trained”; and “a convolutional neural network (CNN) trained to identify probabilities of accuracy when using candidate fault dynamic models based on data associated with the target bearing” are not sufficient to integrate the abstract idea into a practical application. The alleged improvement in the functioning of the machine learning models and the technological field of bearing fault prognosis relates to improvement to the abstract idea itself. Therefore, the current claims do not recite additional elements that are indicative of integration of an abstract idea into a practical application.
The applicant argues on pages 10-11 of the remark filed that “The eligibility of amended claim 1 is directly supported by analogy to USPTO Subject Matter Eligibility Example 48. In Example 48, the USPTO analyzed a method for separating speech signals using a Deep Neural Network (DNN), and determined that claim 1 was ineligible because it merely invoked a generic DNN to perform mathematical calculations without detailing how the DNN solved a technical problem. However, the USPTO indicated that claim 2 of Example 48 was patent-eligible at Step 2A, Prong 2 because it added specific data transformation and processing steps. Specifically, such approved claim 2 included converting the signal into a spectrogram using a short-time Fourier transform (STFT), deriving temporal features, using the DNN to cluster the features, applying binary masks, and synthesizing speech waveforms. The USPTO concluded that this ordered combination of preparing specific data structures for the neural network, and subsequently processing them, reflected the technical improvement described in the specification and integrated the abstract idea into a practical application. Therefore, amended claim 1 is directly analogous to the eligible Claim 2 of Example 48. In particular, analogous to eligible claim 2 in Example 48, presently amended claim 1 requires specific pre-processing including fusing CWCM energy spectrums with operating conditions to create bearing information maps to improve the accuracy and training convergence speed of the CNNs.”
The Examiner agrees with applicant’s remark on claim 1 of Example 48. However, the Examiner respectfully disagrees applicant’s argument on claim 2 for Example 48. Claim 2 of Example 48 recites a judicial exception the same as claim 1 but is eligible because the claim as a whole improves speech-separation technology and thus integrates the exception into a practical application of separating speech and is therefore not “directed to” the judicial exception. However, the additional elements of the present claims do not integrate an abstract idea into a practical application as shown in the rejection. Therefore, the claim 2 for Example 48 is dissimilar to the claims limitations of the present application.
The applicant argues on pages 11-12 of the remark filed that “… Alternatively, should the USPTO not be convinced by the Step 2A analysis outlined above, it is submitted that the analysis should proceed to Step 2B to determine if the additional elements amount to significantly more than any asserted abstract idea itself. Since the claim is argued to pass at Step 2A Prong 2, Applicants submit that the elements that provide the practical application are carried over and evaluated. In this instance, Applicants submit that the claimed data processing and neural network steps respectfully provide "significantly more" than any asserted abstract idea and satisfies 35 U.S.C. §101.”
The Examiner respectfully disagrees applicant’s argument. Significantly more can be demonstrated by additional elements that are not well-understood and conventional that integrate the abstract idea into a practical application. However, the claims do not recite them. The limitation of “inputting the fused bearing information maps into a machine-learned start-to-prognosis (STP) fault detection convolutional neural network (CNN) trained”; and “a convolutional neural network (CNN) trained to identify probabilities of accuracy when using candidate fault dynamic models based on data associated with the target bearing” are routine in bearing fault diagnosis and prognosis; and are well-understood and conventional. Therefore, the claims 1, 8, and 17 do not contain additional elements that are not well-understood and conventional that integrate the abstract idea into a practical application.
Dependent claims 2-7, 9-16, and 18 provide additional features/steps which are considered part of an expanded abstract idea of the independent claims, and do not integrate the abstract ideas into a practical application. Therefore, claims 2-7, 9-16, and 18 are also patent ineligible.
Hence, the Examiner submits that the rejections of Claims 1-18 are proper.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-2, 4-9, and 11-18 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
As to claim 1, the claim recites “A hybrid methodology for bearing fault diagnosis and prognosis (FDP), comprising:
monitoring a target bearing to obtain vibration data from the target bearing;
forming continuous wavelet coefficient matrices (CWCM) from the vibration data and monitoring operating condition information of the target bearing;
creating fused bearing information maps comprising an energy spectrum of the CWCM and the operating condition information;
inputting the fused bearing information maps into a machine-learned start-to-prognosis (STP) fault detection convolutional neural network (CNN) trained to diagnose an occurrence of a fault in the target bearing based on the fused bearing information maps;
when a fault is diagnosed by the STP fault detection CNN, triggering operation of a machine-learned fault model-selection convolutional neural network (CNN) trained to identify probabilities of accuracy when using candidate fault dynamic models based on data associated with the target bearing; and
fusing results from one or more fault models with particle filter (PF) based analysis to produce prognosis of remaining useful life (RUL) for the target bearing.”
Under the Step 1 of the eligibility analysis, we determine whether the claim is directed to a statutory category by considering whether the claimed subject matter falls within the four statutory categories of patentable subject matter identified by 35 U.S.C. 101: Process, machine, manufacture, or composition of matter. The above claim is considered to be in a statutory category (process for claims 1 and 17, and apparatus for claim 8).
Under the Step 2A, Prong One, we consider whether the claim recites a judicial exception (abstract idea). In the above claim, the bold type portion constitutes an abstract idea because, under a broadest reasonable interpretation, it recites limitations that fall into/recite an abstract idea exceptions. Specifically, under the 2019 Revised Patent Subject matter Eligibility Guidance, it falls into the grouping of subject matter when recited as such in a claim that covers mathematical concepts (mathematical relationships, mathematical formulas or equations, mathematical calculations).
In claim 1, the steps identified in bold type are mathematical concepts, therefore, they are considered to be abstract idea.
Next, under the Step 2A, Prong Two, we consider whether the claim that recites a judicial exception is integrated into a practical application.
In this step, we evaluate whether the claim recites additional elements that integrate the exception into a practical application of that exception.
The claim comprises the following additional elements:
monitoring a target bearing to obtain vibration data from the target bearing; inputting the fused bearing information maps into a machine-learned start-to-prognosis (STP) fault detection convolutional neural network (CNN) trained; and a convolutional neural network (CNN) trained to identify probabilities of accuracy when using candidate fault dynamic models based on data associated with the target bearing.
The additional element “monitoring a target bearing to obtain vibration data from the target bearing” represents necessary data gathering and does not integrate the limitation into a practical application. The additional elements “inputting the fused bearing information maps into a machine-learned start-to-prognosis (STP) fault detection convolutional neural network (CNN) trained”; and “a convolutional neural network (CNN) trained to identify probabilities of accuracy when using candidate fault dynamic models based on data associated with the target bearing” are not sufficient to integrate the abstract idea into a practical application because they only add insignificant extra-solution activities to the judicial exception.
In conclusion, the above additional elements, considered individually and in combination with the other claims elements do not reflect an improvement to other technology or technical field, do not reflect improvements to the functioning of the computer itself, do not recite a particular machine, do not effect a transformation or reduction of a particular article to a different state or thing, and, therefore, do not integrate the judicial exception into a practical application. Therefore, the claim is directed to a judicial exception and require further analysis under the Step 2B.
The above claim, does not include additional elements that are sufficient to amount to significantly more than the judicial exception because they are generically recited and are well-understood/conventional in a relevant art as evidenced by the prior art of record (Step 2B analysis).
For example, monitoring a target bearing to obtain vibration data from the target bearing is considered necessary data gathering. As recited in MPEP section 2106.05(g), necessary data gathering (i.e. receiving data) is considered extra solution activity in light of Mayo, 566 U.S. at 79, 101 USPQ2d at 1968; OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015).
For example, inputting the fused bearing information maps into a machine-learned start-to-prognosis (STP) fault detection convolutional neural network (CNN) trained is disclosed by “Liu CN 111855195A”, Abstract, [0011], [0029], [0053,] [0057], [0065], [0088], [0037]; and “Xu WO2022077901A1”, Abstract; [0011], [0049], [0060], [0077], [0107], Claim 1.
The claim, therefore, is not patent eligible.
Independent claims 8 and 17 recite subject matter that is similar or analogous to that of claim 1, and therefore, the claim is also patent ineligible.
With regards to the dependent claims, claims 2, 4-7, 9, 11-16, and 18 provide additional features/steps which are considered part of an expanded abstract idea of the independent claims, and do not integrate the abstract ideas into a practical application.
The dependent claims are, therefore, also not patent eligible.
Examiner’s Note
Regarding Claims 1-2, 4-9, and 11-18, the most pertinent prior arts are “Liu CN 111855195A”; “Xu WO 2022077901A1”; “Wang CN 115130495A”; “Chen et al. (Multiscale Convolutional Neural Network With Feature Alignment for Bearing Fault Diagnosis, IEEE, published May 5, 2021)”; “Cui et al. (Comprehensive Remaining Useful Life Prediction for Rolling Element Bearings Based on Time Varying Particle Filtering, IEEE, published March 29, 2022)”; “Pan et al. (A two-stage method based on extreme learning machine for predicting the remaining useful life of rolling element bearings, ScienceDirect, published April 23, 2020)”.
As to claims 1, 8, and 17, Liu teaches monitoring a target bearing to obtain vibration data from the target bearing (Liu, Abstract, [0011], [0029], [0033]);
processing the vibration data into processed data (Liu, [0029], [0031], [0037]);
inputting data into a machine-learned start-to-prognosis (STP) fault detection convolutional neural network (CNN) trained to diagnose the occurrence of a fault in the target bearing based on the processed data (Liu, Abstract, [0010], [0029], [0037], [0040], [0041], [0061]).
Wang teaches fusing results from one or more fault models with particle filter (PF) based analysis to produce prognosis of remaining useful life (RUL) for the target bearing (Wang, [0003], [0005], [0033], [0073], [0079], [0100]).
However, the prior arts of record, alone or in combination, do not fairly teach or suggest “forming continuous wavelet coefficient matrices (CWCM) from the vibration data and monitoring operating condition information of the target bearing”;
“creating fused bearing information maps comprising an energy spectrum of the CWCM and the operating condition information”;
“inputting the fused bearing information maps into a machine-learned start-to-prognosis (STP) fault detection convolutional neural network (CNN) trained to diagnose an occurrence of a fault in the target bearing based on the fused bearing information maps”;
“when a fault is diagnosed by the STP fault detection CNN, triggering operation of a machine-learned fault model-selection convolutional neural network (CNN) trained to identify the probabilities of accuracy when using candidate fault dynamic models based on data associated with the target bearing” including all limitations as claimed.
Dependent claims 2, 4-7, 9, 11-16, and 18 are also distinguish over the prior art for at least the same reason as claims 1, 8, and 17.
Examiner notes, however, that claims 1-2, 4-9, and 11-18 are rejected under 35 U.S.C. 101, and therefore, not patent eligible.
Conclusion
THIS ACTION IS MADE FINAL. 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 nonprovisional extension fee (37 CFR 1.17(a)) 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 mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LAL CE MANG whose telephone number is (571)272-0370. The examiner can normally be reached Monday to Friday- 8:30-12:00, 1:00-5:30 EST.
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, Catherine T Rastovski can be reached at (571) 270-0349. 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.
/LAL CE MANG/Examiner, Art Unit 2857
Prosecution Insights