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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on -07/19/2024- is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 7 and 16 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 7 and 16 recites a term “dense layer”. It is unclear what type of layer to be regarded as a dense layer. Examiner considers multiple layers as dense layers. Applicants are suggested to remove the unclear term or provide an explanation.
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 thereof, subject to the conditions and requirements of this title.
Claims 1-18 are rejected under 35 U.S.C 101 because the claimed invention is directed to judicial exception (i.e., a law of nature, natural phenomenon, or an abstract idea) without significantly more.
Specifically, claim 1 recites:
An apparatus, comprising:
at least one processor configured to: acquire at least one audio signal comprising audio of a rotating mechanical device; and
transform the audio signal into a vibration data signal using a trained model, wherein the vibration data indicates vibration information of the rotating mechanical device.
The claim limitations in the abstract idea have been highlighted in bold above.
Under the step 1 of the eligibility analysis, it is determined whether the claims are drawn to a statutory category by considering whether the claimed subject matter fall 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 in the statutory category of (machine).
Under step 2A, prong one, it is considered whether the claim recites a judicial exception (abstract idea). In the above claim, the highlighted portion constitutes an abstract idea because, under a broadest reasonable interpretation, it recites limitations that fall into/recite an abstract idea exception. Specifically, under the 2019 Revised Patent Subject Matter Eligibility Guidance, it falls into groupings of subject matter when recited as such in a claim limitation, that cover mathematical concepts (mathematical relationships, mathematical formulas or equations, mathematical calculations) and mental process – concepts performed in the human mind including an observation, evaluation, judgement, and/or opinion.
For example, a step of “transform the audio signal into a vibration data signal using a trained model, wherein the vibration data indicates vibration information of the rotating mechanical device.” is treated by the Examiner as belonging to a mathematical step.
Similar limitations comprise the abstract ideas of the independent claim 10.
Next, under step 2A, prong two, it is considered whether the claim that recites a judicial exception is integrated into a practical application.
In this step, it is evaluated whether the claim recites meaningful additional elements that integrate the exception into a practical application of that exception.
In claim 1, the additional elements/steps is a processor. The above additional elements/steps (hardware– processor) are recited in generality and represent extra solution activity to the judicial exception. The additional element in the preamble of “An apparatus…” is not qualified for a meaningful limitation because it only generally links the use of the judicial exception to a particular technological environment or field of use. The additional elements/steps “acquire at least one audio signal…” is also recited in generality which seem to merely be gathering data and not really performing any kind of inventive step to provide any meaningful additional element. Also, it represents an extra-solution activity to the judicial exception. All uses of judicial exception require it.
In claim 10, the additional elements/steps (computation device) recite similar additional elements/steps as of claim 1. The additional elements/steps (program/software – method) are recited in generality and represent extra- solution activity to the judicial exception. The additional element in the preamble of “A method…” is not qualified for a meaningful limitation because it only generally links the use of the judicial exception to a particular technological environment or field of use. The additional elements/steps “acquiring, by a computational…” are also recited in generality which seem to merely be gathering data and not really performing any kind of inventive to provide any meaningful additional element. Also, it represents an extra-solution activity to the judicial exception. All uses of judicial exception require it.
In conclusion, the above additional elements, considered individually and in combination with the other claim elements do not reflect an improvement to other technology or technical field, and, therefore, do not integrate the judicial exception into a practical application. Therefore, the claims are directed at a judicial exception and require further analysis under step 2B.
However, as evidenced by the prior art of record, the above claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception (step 2B analysis).
Please see prior art rejections below.
Considering claim 1 as a whole, one of ordinary skill in art would not know the practical application of the present invention since the claims do not apply or use the judicial exception in some meaningful way.
The independent claims, therefore, are not patent eligible.
With regards to the dependent claims, the claims 2-9,11-18 comprise the analogous subject matter and also comprise additional features/steps which are the part of an expanded abstract idea of the independent claims (additionally comprising mathematical relationship/mental process steps) and, therefore, the dependent claims are not eligible without additional elements that reflect a practical application and qualified for significantly more for substantially similar reason as discussed with regards to claim 1 and 10.
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) 1, 8, 9, 10, 17, 18 is/are rejected under 35 U.S.C. 102 (a) (1) as being unpatentable over Scanlon, P., Kavanagh, D. F., & Boland, F. M. Residual Life Prediction of Rotating Machines Using Acoustic Noise Signals. IEEE Transactions on Instrumentation and Measurement, vol. 62, no. 1, pp. 95–108, 2013. DOI: 10.1109/tim.2012.2212508 herein after “Scanlon”.
Regarding claim 1, Scanlon teaches an apparatus, comprising:
at least one processor (left col. section II. Acoustic signal processing) configured to:
acquire at least one audio signal comprising audio of a rotating mechanical device (page 100, right col. section III. Experimental setup and implementation: Fig. 3 shows the rotating machine being monitored; the acoustic signals generated by the machine are captured using a suitably placed microphone transducer).
transform the audio signal using a trained model, wherein the data indicates vibration information of the rotating mechanical device (page 100, right col. section III. Experimental setup and implementation: These analog signals are converted to digital signals using an ADC. Signal feature extraction is then performed using approaches described in Section III-B. Using these features, classification training and testing is then performed to generate RUL estimates for the machine as described in Section III-D.
page 97, left col. II. Acoustic signal processing: As the machine degrades over time, defects in the REBs such as cracks or spalls occur generating vibrations in the spectrum. The frequency at which these vibrations occur is termed the characteristic defect frequency (CDF). As a result, the spectrum of the acoustic REB noise signal contains a series of harmonic frequency components.
Page 97, right col. section B. EA: EA is one of the most predominant feature extraction approaches cited in the literature in the field of diagnostic monitoring of rotating machinery [19], [33], [34]. The EA approach involves filtering the signal around the spectral region of interest. The CDFs themselves are typically swamped within the low-frequency broadband noise that is inherently present in mechanical systems…. This envelope signal is then analyzed in the frequency domain by taking the STFT. In the frequency domain, the effect of this enveloping process has on this band limited signal is to shift the spectral components to ‘baseband,’ i.e., down to 0 Hz (dc). That is, the process effectively finds the spectral repetition present (harmonics), resulting in an envelope spectrum that will have a peak at the CDF (fo fundamental) of the fault and at integer multiples of this 2fo, 3fo).
From above paragraphs and Fig. 3 examiner views a machine vibration frequency, i.e. characteristic defect frequency (CDF) corresponds to the acoustic signal (with ambient noise, sensor noise) obtained from the machine. In fig. 3 the acoustic signal is processed to extract acoustic signal into an envelope spectrum that corresponds to a peak at the CDF (i.e., in vibration signal) using a trained model.
However, Scanlon does not explicitly disclose using a trained model to transform the audio signal into a vibration signal.
Therefore, it would be obvious to modify Scanlon to transform the processed acoustic signal corresponding to the CDF as a vibration signal using a trained model (The frequency at which these vibrations occur is termed the characteristic defect frequency (CDF), page 97).
Regarding claim 8, Scanlon teaches the apparatus according to claim 1, wherein the trained model implements a discrete short-time Fourier transform to transform the audio signal into the vibration data signal (page 96 left col. line 2. frequency (time-frequency) domain techniques such as short time Fourier transform (STFT) and wavelet transform [6], [10], [13]– [16]. Envelope analysis (EA) is another spectral-based feature extraction technique widely reported in the literature for detection and diagnosis of bearing defects using the machines vibration signal.
Please see Fig. 3, the signal feature extraction trained model.
Page 101 right col. section B. line 18 For the EA feature extraction approach used in this study, fixed frequency bands were used for selecting… The STFT was computed to obtain the envelope spectrum).
In fig. 3 examiner views, the acoustic signal is processed using STFT to extract acoustic signal into an envelope spectrum that corresponds to a peak at the CDF (i.e., in vibration signal) using a trained model.
However, Scanlon does not explicitly disclose using a trained model to transform the audio signal into a vibration signal.
Therefore, it would be obvious to modify Scanlon to transform the processed acoustic signal corresponding to the CDF as a vibration signal using a trained model with STFT (The frequency at which these vibrations occur is termed the characteristic defect frequency (CDF), page 97).
Regarding claim 9, Scanlon teaches the apparatus according to claim 1, wherein the at least one audio signal is acquired from an audio recorder located in a proximity of the rotating mechanical device (page 100, right col. section III. Experimental setup and implementation: Fig. 3 shows the rotating machine being monitored; the acoustic signals generated by the machine are captured using a suitably placed microphone transducer).
Claims 10, 17, 18 are rejected as claims 1, 8 and 9 respectively having same claim limitations.
Claim(s) 3, 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Scanlon in view of “Grebenik, J., Zhang, Y., Bingham, C., & Srivastava, S. (2016). Roller element bearing acoustic fault detection using smartphone and consumer microphones. [Conference paper/Contribution], School of Engineering, University of Lincoln” herein after “Grebenik”.
Regarding claim 3, Scanlon teaches the apparatus according to claim 1, Scanlon teaches sound data provided by an external source (page 100, right col. section III. Experimental setup and implementation: Fig. 3 shows the rotating machine being monitored; the acoustic signals generated by the machine are captured using a suitably placed microphone transducer),
Scanlon does not teach wherein the trained model is trained using a vibration data obtained by a sensor located on the rotating mechanical device.
Grebenik teaches wherein the trained model is trained using a vibration data obtained by a sensor located on the rotating mechanical device (please see fig. 1 in page 4, an experimental set up, where the vibration sensor is attached to the machine. Fig. 3 shows a trained model using a vibration signal of 16000hz).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing of the invention to have incorporated Grebenik into Clarke for the purpose of detecting vibration of a machine by attaching a vibration sensor into the machine so that the signals can be separately analyzed using a trained model.
Claim 12 is rejected as claim 3 having same claim limitations.
Claim(s) 4, 5, 13, 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Scanlon in view of Cui et al US 20230123117 A1 herein after “Cui”.
Regarding claim 4, Scanlon teaches the apparatus according to claim 1, Scanlon does not teach wherein the at least one processor is further configured to: output the transformed vibration signal to a classifier which classifies whether the vibration information indicates a healthy vibration or a faulty vibration of the rotating mechanical device.
Cui teaches wherein the at least one processor is further configured to: output the transformed vibration signal to a classifier which classifies whether the vibration information indicates a healthy vibration or a faulty vibration of the rotating mechanical device (para [0058] Illustratively, as shown in FIG. 5, a flowchart for recognizing the frequency spectrogram based on the damage recognition model is shown. The background server inputs the frequency spectrogram 51 into a convolution and pooling layer 52 of the model, and maps the frequency spectrogram to a feature space by convolution and pooling to obtain an image feature of the frequency spectrogram; inputs the above image feature into a feature conversion layer 53 for feature conversion to obtain the converted image feature; then inputs the converted image feature into a fully-connected layer 54, and obtains a feature classification result by recognizing and classifying the converted image feature by the fully-connected layer 54; and finally obtains the damage recognition result by normalizing the feature classification result based on an output layer 55. The damage recognition result includes the damage type of the wind turbine blade.).
Examiner views the spectrogram as the transformed vibrational signal from a sound signal. The spectrogram is supplied to the classifier to classify a damage type (i.e., healthy vibration or faulty vibration) in a rotating machine (i.e., wind turbine).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing of the invention to have incorporated Cui into Scanlon for the purpose of detecting fault type of a machine by using a vibration data into a classifier so that the accurate faulty or healthy vibration condition of the turbine can be determined.
Regarding claim 5, the combination of Scanlon and Cui teach the apparatus according to claim 4, Cui teaches further comprising the classifier, wherein the at least one processor operates as the classifier (para [0018] the processor is configured to load and execute the executable instruction stored in the memory to perform the method for inspecting the wind turbine blade as described above.).
Examiner views processor(s) is implemented to perform the instructions of monitoring a machine which also include as a function of classifier.
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing of the invention to have incorporated Cui into Scanlon for the purpose of using separate processors for a classification function so that the various operations in the detection system can be operated separately by multiple processors without any disturbances.
Claim 13 and 14 are rejected as claim 4 and 5 respectively for having same claim limitations.
Claim(s) 6, 7, 15 and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Scanlon in view of Raghavan et al US 20210224633 A1 herein after “Raghavan”.
Regarding claim 6, Scanlon teaches the apparatus according to claim 1, Scanlon does not teach wherein the trained model is a self-organized operational neural network.
Raghavan teaches wherein the trained model is a self-organized operational neural network (para [0088] The previous section demonstrates that multi-layered pooling networks can be successfully grown from a single unit. This section shows that these networks are functional.
[0089] This section demonstrates functionality of networks grown and self-organized from a single unit (FIG. 7C) by evaluating their train and test accuracy on a classification task.)
Examiner views a trained model implemented in the present invention improve the learning of a system by implementing a self-organized operational neural network (Self-ONNs).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing of the invention to have incorporated Raghavan into Scanlon for the purpose of monitoring a rotating machine using trained model that is a self-organized operational neural network so that the learning or training of the model can be improved without human intervention.
Regarding claim 7, Scanlon teaches the apparatus according to claim 1, Scanlon does not teach wherein the trained model is comprised of a plurality of operational layers and is cascaded with a self-organized operational neural network classifier comprising a plurality of additional operational layers and one or more dense layers.
Raghavan teaches wherein the trained model is comprised of a plurality of operational layers and is cascaded with a self-organized operational neural network classifier comprising a plurality of additional operational layers and one or more dense layers. (Claim 1. A method for constructing a neural network comprising: under control of a hardware processor: growing, from at least one node, a plurality of layers of a neural network each comprises a plurality of nodes; and self-organizing the plurality of layers of the neural network.
Claim 6. The method of claim 1, wherein growing, from the at least one node, the plurality of layers of the neural network comprises dividing the at least one node to generate a daughter node, of the at least one node, in the higher second layer.
Claim 25. The method of claim 1, comprising training a classifier connected to the plurality of layers and/or the neural network).
From above claims from Raghavan, examiner views that a trained machine learning architecture has multiple operational layers following a self-organized neural network classifier. The self-organized neural network classifier comprises connecting to the multiple operational layers.
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing of the invention to have incorporated Raghavan into Scanlon for the purpose of monitoring a rotating machine using trained model that is a self-organized operational neural network so that the learning or training of the model and classification of output/result can be self-improved by the model without human intervention.
Claim 15 and 16 is rejected as claim 6 and 7 respectively having same claim limitations.
Allowable Subject Matter
There are no prior art rejections for claims 2 and 11. However, examiner cannot comment on their allowability until the rejections under USC 101 are adequately addressed.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Clarke et al US 20060122809 A1 discusses monitoring motor using vibration signal.
Kamiya et al US 20170293862 A1 discusses monitoring machine health using machine learning.
Nakagawa US 20220187916 A1 discusses converting sound signal to vibration signal.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHARAD TIMILSINA whose telephone number is (571)272-7104. The examiner can normally be reached Monday-Friday 9:00-5:00.
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 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.
/SHARAD TIMILSINA/Examiner, Art Unit 2857
/ALEXANDER SATANOVSKY/Primary Examiner, Art Unit 2857
