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 .
Election/Restrictions
Claims 21-32 are withdrawn from further consideration pursuant to 37 CFR 1.142(b), as being drawn to a nonelected Invention II, there being no allowable generic or linking claim. Applicant timely traversed the restriction (election) requirement in the reply filed on April 2, 2026.
Allowable Subject Matter
Claims 8, 9, 18, and 19 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-7, 10-17, and 20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Andoni et al. (US Pub. 20230186053).
Referring to claim 1, Andoni discloses An apparatus for equipment anomaly detection, comprising:
a data acquisition device, acquiring a signal of an equipment during operation [figs. 1-3; pars. 48-52; a system monitors behavior of a monitored system; during operation of the monitored system, sensors associated with the monitored system generate time-series data representative of operation of the monitored system, a preprocessor of the system receives the time-series data];
a storage device, storing a machine learning model [figs. 1-3; pars. 48 and 53-56; the system includes (i.e., stores) various machine-learning models (i.e., a dimensional reduction model comprising an encoder network, a latent-space layer, a latent-space feature model, and a decoder network; a predictive machine-learning model; and an alert generator comprising an anomaly detection model and an alert generation model)]; and
a processor, coupled to the data acquisition device and the storage device [figs. 1-3; pars. 48 and 53-56; the system includes one or more processors executing instructions to obtain the time-series data from the monitored system and evaluate the time-series data using the various machine-learning models], and configured to:
acquire a plurality of signals of the equipment during normal operation in advance by using the data acquisition device to train the machine learning model [figs. 1-3; pars. 30-32, 53, 54, 61-66, 70, 74, 75, and 78-80; the various machine-learning models are trained using training data associated with a normal or recognized operation condition associated with the monitored system];
acquire a real-time signal of the equipment during a current operation by using the data acquisition device [figs. 1-3; pars. 48-52; note the time-series data received during operation of the monitored system]; and
input the acquired real-time signal to the trained machine learning model to output a detection result indicating a current operation state of the equipment [figs. 1-3; pars. 72, 73, 86-90, and 95-102; the time-series data is processed by the various machine learning models to generate an output indicating whether the monitored system has deviated from an inferred operating state (e.g., has entered an anomalous operating state)].
Referring to claim 2, Andoni discloses The apparatus for equipment anomaly detection according to claim 1, wherein the machine learning model [fig. 1-3; pars. 53-56; note the various machine-learning models] is formed by connecting an encoder composed of a neural network to an outlier detection model (ODM) [figs. 1-3; pars. 29, 43, 44, 53-56, 73, 90, and 102; the various machine-learning models include the dimensional reduction model (i.e., an autoencoder, which is a particular type of neural network); the dimensional reduction model is connected to the predictive machine-learning model and the alert generator comprising the anomaly detection model and the alert generation model (to detect deviations / anomalies)], and the processor is configured to input the real-time signal to the encoder for feature extraction and dimension reduction to output compressed representation data [figs. 1-3; pars. 3, 86, and 95; the dimensional reduction model processes the time-series data to generate a dimensionally reduced encoding (i.e., feature vectors) at one or more latent-space layers of the dimensional-reduction model], and input the compressed representation data to the outlier detection model to distinguish the current operation state of the equipment and output the detection result [figs. 1-3; pars. 55, 56, 72, 73, 86-90, and 95-102; output from the dimensional reduction model is provided to the predictive machine-learning model and the alert generator comprising the anomaly detection model and the alert generation model, which generate the output indicating whether the monitored system has deviated from an inferred operating state].
Referring to claim 3, Andoni discloses The apparatus for equipment anomaly detection according to claim 2, wherein the processor is configured to: acquire a plurality of time-domain signals of the equipment during normal operation by using the data acquisition device; and train an autoencoder comprising the encoder and a decoder by using the time-domain signal [figs. 1-3; pars. 30-32, 53, 54, 61-66, 70, 74, 75, and 78-80; note the training of the various machine-learning models, which includes training the dimensional reduction model using training data (e.g., time-series data) associated with a normal or recognized operation condition associated with the monitored system], comprising: performing feature extraction and dimension reduction on the time-domain signal by the encoder to output compressed representation data of the time-domain signal [figs. 1-3; pars. 30-32, 53, 54, 61-66, 70, 74, 75, and 78-80; note the training of the encoder network and the latent-space feature model]; decoding the compressed representation data by the decoder to obtain a reconstructed time-domain signal [figs. 1-3; pars. 30-32, 53, 54, 61-66, 70, 74, 75, and 78-80; note the training of the decoder network]; and calculating a loss function between the time-domain signal and the reconstructed time-domain signal to train the encoder [par. 39; during unsupervised training of an autoencoder (e.g., the dimensional reduction model), a data sample is provided as input to the autoencoder, and the autoencoder reduces the dimensionality of the data sample (which is a lossy operation) and attempts to reconstruct the data sample as output data; the output data is compared to the input data sample to generate a reconstruction loss].
Referring to claim 4, Andoni discloses The apparatus for equipment anomaly detection according to claim 3, wherein the processor is further configured to: input the time-domain signal acquired by the data acquisition device to the trained encoder to output the compressed representation data [figs. 1-3; pars. 30-32, 53, 54, 61-66, 70, 74, 75, and 78-80; note the training of the various machine-learning models, which includes training the dimensional reduction model using training data (e.g., time-series data) associated with a normal or recognized operation condition associated with the monitored system]; and train the outlier detection model by using the compressed representation data [figs. 1-3; pars. 30-32, 53, 54, 61-66, 70, 74, 75, and 78-80; note the training of the various machine-learning models, which includes training the predictive machine-learning model and the alert generator comprising the anomaly detection model and the alert generation model based on output data from the dimensional reduction model].
Referring to claim 5, Andoni discloses The apparatus for equipment anomaly detection according to claim 2, wherein the processor is further configured to: acquire a plurality of frequency-domain signals of the equipment during normal operation by using the data acquisition device; and train an autoencoder comprising the encoder and a decoder by using the frequency-domain signal [figs. 1-3; pars. 30-32, 49, 53, 54, 61-66, 70, 74, 75, and 78-80; note the training of the various machine-learning models, which includes training the dimensional reduction model using training data (e.g., time-series data of frequency measurement values) associated with a normal or recognized operation condition associated with the monitored system], comprising: performing feature extraction and dimension reduction on the frequency-domain signal by the encoder to output compressed representation data of the frequency-domain signal [figs. 1-3; pars. 30-32, 49, 53, 54, 61-66, 70, 74, 75, and 78-80; note the training of the encoder network and the latent-space feature model]; decoding the compressed representation data by the decoder to obtain a reconstructed frequency-domain signal [figs. 1-3; pars. 30-32, 49, 53, 54, 61-66, 70, 74, 75, and 78-80; note the training of the decoder network]; and calculating a loss function between the frequency-domain signal and the reconstructed frequency-domain signal to train the encoder [par. 39; during unsupervised training of an autoencoder (e.g., the dimensional reduction model), a data sample is provided as input to the autoencoder, and the autoencoder reduces the dimensionality of the data sample (which is a lossy operation) and attempts to reconstruct the data sample as output data; the output data is compared to the input data sample to generate a reconstruction loss].
Referring to claim 6, Andoni discloses The apparatus for equipment anomaly detection according to claim 5, wherein the processor is further configured to: input the frequency-domain signal acquired by the data acquisition device to the trained encoder to output the compressed representation data [figs. 1-3; pars. 30-32, 49, 53, 54, 61-66, 70, 74, 75, and 78-80; note the training of the various machine-learning models, which includes training the dimensional reduction model using training data (e.g., time-series data of frequency measurement values) associated with a normal or recognized operation condition associated with the monitored system]; and train the outlier detection model by using the compressed representation data [figs. 1-3; pars. 30-32, 49, 53, 54, 61-66, 70, 74, 75, and 78-80; note the training of the various machine-learning models, which includes training the predictive machine-learning model and the alert generator comprising the anomaly detection model and the alert generation model based on output data from the dimensional reduction model].
Referring to claim 7, Andoni discloses The apparatus for equipment anomaly detection according to claim 5, wherein the frequency-domain signal is obtained by the processor performing fast Fourier transform (FFT) on a time-domain signal acquired by the data acquisition device or is directly acquired by the data acquisition device [pars. 49-51; the preprocessor may generate the time series of frequency measurement values by performing a time-domain to frequency-domain transformation (e.g., a Fast Fourier Transform)].
Referring to claim 10, Andoni discloses The apparatus for equipment anomaly detection according to claim 1, wherein the signal comprises a voltage signal, a current signal, a sound signal, or a vibration signal [par. 49; the time-series data includes a time series of temperature measurement values, a time series of vibration measurement values, a time series of voltage measurement values, a time series of amperage measurement values, a time series of rotation rate measurement values, a time series of frequency measurement values, a time series of packet loss rate values, a time series of data error values, a time series of pressure measurement values, measurements of other mechanical, electromechanical, electrical, or electronic metrics, or a combination thereof].
Referring to claim 11, see the rejection for claim 1, which incorporates the claimed method.
Referring to claim 12, see the rejection for claim 2.
Referring to claim 13, see the rejection for claim 3.
Referring to claim 14, see the rejection for claim 4.
Referring to claim 15, see the rejection for claim 5.
Referring to claim 16, see the rejection for claim 6.
Referring to claim 17, see the rejection for claim 7.
Referring to claim 20, see the rejection for claim 10.
Conclusion
The following prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Liebman (US Pub. 20230085991) discloses anomaly detection based on a time-series signal using neural networks.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GRACE PARK whose telephone number is (571)270-7727. The examiner can normally be reached M-F 8AM-5PM.
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, TAMARA KYLE can be reached at (571)272-4241. 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.
/Grace Park/Primary Examiner, Art Unit 2144
Prosecution Insights