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 .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Claim Objections
Claims 1 – 13, 15, and 16 are objected to because of the following informalities. In order to provide consistent terminology and element relationships, the claims should be corrected as suggested:
(Currently Amended) A method for monitoring [[the]] operational condition of rotating electrical machines and automatic detection of mechanical and electrical faults,
a. collecting data (510) from [[the]] electrical current and voltage signals (505) of a rotating electrical machine (301) with a data acquisition module (101);
b. transferring the data collected by the data acquisition module (101) to [[the]]a gateway device (102);
c. in the gateway device (102), performing the steps of:
i. data compression (515);
ii. data encryption (520); and
iii. transferring data to [[the]]a cloud processing center (525) via [[the]] internet (107);
d. in the processing center (103), performing the steps of:
i. data decoding (605);
ii. applying [[the]] Fast Fourier Transform (FFT) (610) to obtain [[the]] frequency domain representation;
iii. subsampling in [[the]] time domain (615); and
iv. extracting features from the electrical current and voltage signals in the time and frequency domains (620);
e. in the processing center (103), performing the step of conducting [[the]] anomaly detection [[step]] on the electrical current and voltage signals using one or more statistical techniques and one or more machine learning techniques (625);
f. in the processing center (103), in case of detected anomaly, performing the step of executing [[the step of]] identifying the operational condition of [[the]]a machine and fault classification using one or more machine learning techniques (640).
(Currently Amended) The method according to claim 1, wherein the data acquisition module (101) is installed inside [[the]]a motor control cabinet[[,]] (305), and collects electrical current and voltage signals (505) from [[a]]the rotating electrical machine (301) with current transformers (CTs) (302) and branching points on [[the]] conductors (303) installed alongside [[the]] phase conductors for voltage sensing, also inside the motor control cabinet (305).
(Currently Amended) The method according to claim 1, wherein the step of anomaly detection in the electrical current and voltage signals using one or more statistical techniques and one or more machine learning techniques (625) includes [[the]]a technique called Principal Component Analysis (PCA) and includes an autoencoder neural network.
(Currently Amended) The method according to claim 1, wherein the step of identifying the operational condition of [[the]]a machine and fault classification using one or more machine learning techniques (640) includes convolutional neural networks and one or more boosting algorithms based on decision trees.
(Currently Amended) The method according to claim 1, further comprising obtaining operator validation (830) regarding [[the]] detected faults, and inserting the received operator validation, together with new collected data from [[the]]a faulty machine, into the training process of [[the]] machine learning models (805).
(Currently Amended) The method according to claim 1, wherein [[the]] data transfer between the data acquisition module (101) and the gateway device (102) occurs remotely through a local communication network (106) wirelessly or wired.
(Currently Amended) The method according to claim 1, wherein the rotating electrical machine is one of: an induction electric motor, a generator, a pump, a fan, a conveyor belt, an agitator, a reducer, an elevator, a turbine, a compressor, a gearbox.
(Currently Amended) The method according to claim 1, wherein the operational condition of the rotating electrical machine includes one of: wear, risks, and faults in bearings, bearing failure, eccentricities, broken bars in the rotor, shaft misalignment, shaft unbalance, shaft clearance, soft foot, overload, voltage transients, phase unbalance, harmonic distortion, Sigma currents, pump cavitation, pump clogging, corrosion of parts, resonance, seal assembly failure, leakage, rotational looseness, structural looseness, operator error.
(Currently Amended) A system for monitoring [[the]] operational condition of rotating electrical machines and automatic detection of mechanical and electrical faults,
a. a data acquisition module (101) for collecting electrical current and voltage signals and transferring [[the]] data of electrical current and voltage signals to [[the]]a gateway device (102);
b. [[a]]the gateway device (102) for compressing [[the]] electrical current and voltage data, encrypting the electrical current and voltage data, and transferring the electrical current and voltage data to [[the]]a processing center (103);
c. [[a]]the processing center (103) on a cloud computing platform (104):
i. wherein the electrical current and voltage data is decoded (605);
ii. wherein Fast Fourier Transform (FFT) is performed (610);
iii. wherein the electrical current and voltage data is subsampled in [[the]] time domain (615);
iv. wherein attributes of the electrical and voltage signals are extracted in the time and frequency domains (620);
v. wherein one or more statistical techniques and one or more machine learning techniques are implemented for anomaly detection in the electrical current and voltage signals (625);
vi. wherein one or more machine learning techniques are implemented for identifying the operational condition of [[the]]a machine and fault classification (640).
(Currently Amended) The system according to claim 9, wherein the data acquisition module (101) is installed in [[the]]a motor control cabinet (305) and collects electrical current and voltage data from a rotating electrical machine (301) with CTs (303) and voltage transformers (304) installed alongside [[the]] phase conductors that power the rotating electrical machine (301).
(Currently Amended) The system according to claim 9, wherein the processing center (103) is adapted to perform Principal Component Analysis (PCA) and an autoencoder neural network in [[the]]an anomaly detection step using one or more statistical techniques and one or more machine learning techniques (625).
(Currently Amended) The system according to claim 9, wherein the processing center (103) is adapted to apply convolutional neural networks and one or more boosting algorithms based on decision trees in [[the]]a step of identifying the operational condition of the machine and fault classification using one or more machine learning techniques (640).
(Currently Amended) The system according to claim 9, wherein the processing center is adapted to obtain operator validation (830) regarding [[the]] detected faults, and insert [[the]] received validation, together with new collected data from [[the]] faulty machine, into [[the]] training process of the machine learning models (805).
(Currently Amended) The system according to claim 9, wherein [[the]]a rotating electrical machine (301) is one of: an induction electric motor, a generator, a pump, a fan, a conveyor belt, an agitator, a reducer, an elevator, a turbine, a compressor, a gearbox.
(Currently Amended) The system according to claim 9, wherein the operational condition of the rotating electrical machine includes one of: wear, risks, and faults in bearings, bearing failure, eccentricities, broken bars in the rotor, shaft misalignment, shaft unbalance, shaft clearance, soft foot, overload, voltage transients, phase unbalance, harmonic distortion, Sigma currents, pump cavitation, pump clogging, corrosion of parts, resonance, seal assembly failure, leakage, rotational looseness, structural looseness, operator error.
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 7, 8, 15, and 16 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
Claims 7 and 15 recite that "the rotating electrical machine" is "an induction electric motor, a generator, a pump, a fan, a conveyor belt, an agitator, a reducer, an elevator, a turbine, a compressor, a gearbox." The list lacks a conjunction establishing whether the listed items are alternatives or cumulative requirements. Moreover, the Specification distinguishes a rotating electrical machine, such as an electric motor or generator, from associated driven or driving equipment, such as a pump, fan, conveyor belt, agitator, reducer, elevator, compressor, or gearbox. It is therefore unclear whether the claims require the rotating electrical machine itself to be each listed device, or whether the claims are intended to encompass an electrical machine together with associated driven or driving equipment. The metes and bounds of the claimed subject matter are consequently uncertain. See Claim objection above.
Claims 8 and 16 recite that the operational condition of the machine "includes wear, risks, and faults in bearings, bearing failure, eccentricities, broken bars in the rotor, shaft misalignment, shaft unbalance, shaft clearance, soft foot, overload, voltage transients, phase unbalance, harmonic distortion, Sigma currents, pump cavitation, pump clogging, corrosion of parts, resonance, seal assembly failure, leakage, rotational looseness, structural looseness, operator error." The list lacks a conjunction establishing whether the conditions are alternatives or cumulative requirements. In addition, the term "risks" does not identify a machine fault or objectively bounded operational condition and conflicts with the Specification, which recites "scratches." The claims also recite "operator error," while the Specification recites "operator failure," without defining the electrical-signal condition or objective criterion by which such an operator-related condition is identified. Accordingly, one of ordinary skill in the art would not be reasonably apprised of the scope of the claimed operational conditions. Sigma currents are not included as a basis for this rejection because the Specification expressly defines Sigma currents as parasitic currents present in motor conductors that can reduce efficiency and motor life. See Claim objection above.
For purposes of examination only, the examiner interprets the lists in claims 7, 8, 15, and 16 as reciting alternatives rather than cumulative requirements; interprets pumps, fans, conveyor belts, agitators, reducers, elevators, compressors, and gearboxes as equipment driven by or coupled to a rotating electrical machine; interprets "risks" as the disclosed term "scratches"; and interprets "operator error" broadly as a machine operational condition caused by operator action. These interpretations permit examination to proceed but do not cure the indefiniteness identified above.
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 1–16 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to a judicial exception (i.e., an abstract idea) without significantly more.
Representative claim 1 recites: A method for monitoring the operational condition of rotating electrical machines and automatic detection of mechanical and electrical faults, comprising the steps of:
a. collecting data from the electrical current and voltage signals of a rotating electrical machine with a data acquisition module ;
b. transferring the data collected by the data acquisition module to the gateway device ;
c. in the gateway device , performing the steps of:
i. data compression ;
ii. data encryption ; and
iii. transferring data to the cloud processing center via the internet ;
d. in the processing center , performing the steps of:
i. data decoding ;
ii. applying the Fast Fourier Transform (FFT) to obtain the frequency domain representation;
iii. subsampling in the time domain ; and
iv. extracting features from the signals in the time and frequency domains ; e. in the processing center , conducting the anomaly detection step on the signals using one or more statistical techniques and one or more machine learning techniques ;
f. in the processing center, in case of detected anomaly, executing the step of identifying the operational condition of the machine and fault classification using one or more machine learning techniques.
The claim limitations constituting the abstract idea have been highlighted in bold above. The remaining limitations are treated as additional elements.
Step 1 - Statutory Category
Claim 1 is nominally directed to a method and therefore falls within the statutory process category. Claim 9 is nominally directed to a system comprising physical computing components and therefore falls within the statutory machine category.
Dependent claims 2-8 and 10-16 remain within the statutory category of their respective base claims. The analysis therefore proceeds to Step 2A.
Step 2A, Prong One - Recitation of a Judicial Exception
Independent claim 1 recites "applying the Fast Fourier Transform (FFT) to obtain the frequency domain representation." A Fourier transform is a mathematical calculation that converts a signal representation from the time domain to the frequency domain and therefore falls within the mathematical-concepts grouping of abstract ideas.
Claim 1 further recites "conducting the anomaly detection step on the signals using one or more statistical techniques and one or more machine learning techniques" and, when an anomaly is detected, "identifying the operational condition of the machine and fault classification using one or more machine learning techniques." Under the broadest reasonable interpretation, these limitations encompass evaluating identified signal features to determine whether the signal deviates from a normal condition and assigning the evaluated condition to a fault category. These are evaluations and judgments within the mental-process grouping, even though the claim invokes statistical and machine-learning tools to perform them. The nominal use of a computer or machine-learning model does not remove an otherwise abstract evaluation from the mental-process grouping.
Independent claim 9 recites the corresponding system functions, including that "FFT is performed," that statistical and machine-learning techniques are implemented for anomaly detection, and that machine-learning techniques are implemented for identifying the operational condition and fault classification. A system claim reciting generic components configured to perform the same mathematical calculation and evaluative data analysis recites the same judicial exceptions.
Claims 3 and 11 further recite Principal Component Analysis and an autoencoder neural network for anomaly detection. Principal Component Analysis is a mathematical dimensionality-reduction operation, and the recited autoencoder is invoked at a results-oriented level to analyze and reduce signal data. Claims 4 and 12 further recite convolutional neural networks and boosting algorithms based on decision trees for the evaluative classification.
Claims 5 and 13 further recite receiving an operator's validation and inserting that validation with newly collected data into model training. These limitations further specify mathematical data processing, evaluative judgment, and model training and therefore remain within the identified abstract idea.
Claims 2, 6-8, 10, and 14-16 do not remove the identified mathematical calculation and evaluative data analysis from the claims.
Step 2A, Prong Two - No Integration into a Practical Application
The additional elements of claims 1 and 9 include collecting electrical current and voltage signals from a rotating electrical machine with a data acquisition module; transferring the collected data to a gateway device; compressing, encrypting, and transferring the data through the Internet; using a processing center on a cloud-computing platform to decode and subsample the data; and extracting signal features in the time and frequency domains. Considered individually, the data-acquisition limitation merely obtains the information to be analyzed, and the gateway, Internet, and cloud-computing limitations merely transmit, protect, decode, and prepare that information for the abstract analysis. They do not improve the operation of the rotating electrical machine, the data-acquisition module, the gateway, the Internet, cloud computing, compression, encryption, subsampling, feature extraction, or the machine-learning models themselves.
Considered as an ordered combination, the claims collect specified information, transport and preprocess that information, mathematically analyze it, and produce informational results identifying an anomaly, operational condition, or fault classification. The claims do not require controlling, shutting down, repairing, maintaining, or otherwise changing operation of the rotating electrical machine in response to the analysis. The claimed output is therefore the result of the abstract analysis rather than a physical or technological action applying that result. This information-processing sequence is analogous to the electric-power monitoring claims addressed in Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1353-56 (Fed. Cir. 2016), which collected specified electrical information, analyzed the information, and reported the results without reciting a technological improvement in how those functions were performed.
Claims 2 and 10 place the data-acquisition module in a motor control cabinet and recite CTs together with branching points or voltage transformers. These elements specify the source and physical location from which data are gathered, but the claims do not recite an improvement in the structure or operation of the CTs, voltage transformers, branching points, data-acquisition circuitry, or motor control cabinet. The limitations merely provide the current-and-voltage data required by the abstract analysis and therefore constitute data-gathering activity and a field-of-use limitation rather than an integration of the exception into a practical application.
Claims 6 and 14 merely specify wireless or wired communication through a local network. Claims 7 and 15 limit the environment to listed machines or coupled equipment. Claims 8 and 16 limit the informational result to listed operating conditions or fault categories. Claims 3, 4, 11, and 12 further specify mathematical or machine-learning techniques used to perform the abstract analysis. Claims 5 and 13 add operator evaluation and model retraining but do not require a physical response affecting the monitored machine. These additional limitations, considered separately and in combination with their respective base claims, do not integrate the judicial exception into a practical application.
The Specification describes advantages including high-rate and high-resolution sampling, greater installation safety and convenience, scalable monitoring of multiple coupled machines, more accurate early fault detection, and prevention of production losses or equipment damage.
Claims 1-16, however, do not require a particular sampling rate or resolution, a defined improvement in diagnostic accuracy, a model architecture that improves computer or machine operation, monitoring multiple coupled machines with one device, or an automatic control or maintenance response. The claims therefore do not reflect the identified technological improvements with sufficient specificity to integrate the judicial exception into a practical application.
Step 2B - No Inventive Concept or Significantly More
The additional elements, considered individually, are recited at a high level of generality and perform their ordinary data-acquisition, communication, and computing functions. The examiner relies on Electric Power Group, 830 F.3d at 1355-56, as recognizing that off-the-shelf computer, network, and display technology used to gather, send, analyze, and present electrical-system information does not supply an inventive concept when the claims do not require a new source or type of information, a new analytical technique, or a new use of the resulting information.
The factual determination that the claimed electrical-signal acquisition and remote machine-condition monitoring elements were well-understood, routine, and conventional is further supported by Parlos, U.S. 2010/0169030 A1. Parlos explains that algorithmic approaches for detecting machine conditions from electrical time-series data were available in the literature; that a switchgear-mounted device could process current-and-voltage measurements and transmit processed information wirelessly to a remote computing system for condition detection; and that PTs and CTs were conventionally supplied and conventionally coupled to switchgear buses for connection to monitoring devices (see paragraphs [0009]-[0015]). Parlos further describes MCSA as commonly used, ESA using stator currents and voltages for fault detection, and inexpensive remote monitoring through existing CTs and PTs in motor-control or switchgear centers (see paragraphs [0412]-[0415]).
The factual determination that sensor-based machine-fault evaluation, network or cloud processing, frequency analysis, machine learning, operator input, and retraining were well-understood, routine, and conventional is further supported by Inagaki et al., U.S. 2017/0031329 A1. Inagaki describes as known the detection of industrial-machine abnormalities by comparing sensor output with a threshold and describes known fault-diagnosis methods (see paragraphs [0005]-[0008] and [0039]). Inagaki further discloses operator-provided fault information, sensor data including current and voltage, frequency or time-frequency analysis, network-connected and cloud-based machine learning, fault-condition learning from training data, additional learning from new data, and notifying an operator of fault information (see paragraphs [0012]-[0019], [0040]-[0049], and [0062]-[0066]).
The examiner additionally takes official notice that, before the effective filing date, generic Internet data transfer, lossless data compression, encryption for transmitted data, decoding received data, generic cloud computing, and wired or wireless local-network communication were widely prevalent, well-understood, routine, and conventional data-processing and networking functions when recited, as here, without any particular improved algorithm, protocol, data structure, or hardware architecture. Cella et al., U.S. 2019/0146478 A1, corroborates these conventional functions by disclosing compression and encryption of sensor data for delivery to a cloud server, wired or wireless data transmission, gateway-based Internet communication, and cloud processing (see paragraphs [0403], [1401], and [1712]). Applicant may traverse this official notice in accordance with applicable practice.
Considered as an ordered combination, the additional elements are arranged in their ordinary sequence: sensors acquire machine-related data; a gateway compresses, encrypts, and communicates the data; a remote computing platform decodes and preprocesses the data; and the recited abstract analysis determines and classifies a condition. The references above are cited as factual support for the well-understood, routine, and conventional nature of the additional elements and their ordinary use in remote machine-condition monitoring, not as a substitute for the separate novelty or obviousness inquiry. Nothing in the claims requires an unconventional interaction among those components or changes how any component performs its ordinary function. The additional elements therefore do not amount to significantly more than the judicial exception.
The additional limitations of dependent claims 2-8 and 10-16 likewise do not supply an inventive concept. The CT, PT, cabinet, and switchgear-type arrangements in claims 2 and 10 are conventional data-acquisition arrangements, as expressly supported by Parlos at paragraphs [0014] and [0415]. The wired or wireless network of claims 6 and 14 performs ordinary communication. The listed machine and fault categories of claims 7, 8, 15, and 16 merely restrict the field of use or informational result. The PCA, autoencoder, convolutional-neural-network, and decision-tree-boosting limitations of claims 3, 4, 11, and 12 further specify the mathematical or evaluative analysis itself. The operator validation and retraining limitations of claims 5 and 13 further specify evaluation and training without requiring a technological or physical response. Considered separately and with the ordered combination of their respective base claims, these limitations do not provide an inventive concept.
Accordingly, claims 1-16 are directed to judicial exceptions without integration into a practical application and without additional elements amounting to significantly more. Claims 1-16 are therefore ineligible under 35 U.S.C. 101.7.
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) 1-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Cella et al. (U.S. 2019/0146478 A1, hereinafter Cella) in view of Parlos (U.S. 2010/0169030 A1).
Regarding claim 1, See a method for monitoring the operational condition of rotating electrical machines and automatic detection of mechanical and electrical faults (see an industrial monitoring platform having analog sensors monitoring a rotating machine component and a data-acquisition and analysis circuit that determines the occurrence of an anomalous operating condition using an expert system and a neural network; see paragraph [0014]), comprising the steps of:
a. collecting data from the electrical current and voltage signals of a rotating electrical machine with a data acquisition module (see a local data collection system that collects data from industrial machines and teaches data-acquisition sensors comprising current sensors and voltage sensors; see paragraphs [0198] and [0483]);
b. transferring the data collected by the data acquisition module to the gateway device (see transferring data from a local data collection system through a network to a remote host processing system and teaches local client nodes communicating through a gateway that connects a local area network to the Internet; see paragraphs [0198] and [1712]);
c. in the gateway device, performing the steps of:
i. data compression (see compressing sensor data transmitted through a network to reduce the quantity of transmitted data and network-bandwidth usage; see paragraph [1401]);
ii. data encryption (see encrypting sensor data transmitted through a network to permit secure transmission, including transmission through an alternate or less-secure network path; see paragraph [1401]); and
iii. transferring data to the cloud processing center via the internet (see delivering compressed and encrypted sensor data to a cloud server through a network and teaches a gateway that connects a local area network to the Internet; see paragraphs [1401] and [1712]);
d. in the processing center, performing the steps of:
i. data decoding (See receiving coded data at a receiving system and decoding the received data to reconstruct the original information units; see paragraph [1768]);
ii. applying the Fast Fourier Transform (FFT) to obtain the frequency domain representation (see performing frequency analysis of a signal using a digital Fast Fourier transform; see paragraph [0512]);
iii. subsampling in the time domain (see reducing the sampling frequency of a time-domain waveform and averaging adjacent time-domain sampling points; see paragraph [0256]); and
iv. extracting features from the signals in the time and frequency domains (see extracting information and features from signals using statistical operations, transformations, spectral estimation, modeling, analysis, and feature-extraction techniques; see paragraph [0306]);
e. in the processing center, conducting the anomaly detection step on the signals using one or more statistical techniques and one or more machine learning techniques (see applying mathematical and statistical techniques and machine-learning techniques to industrial sensor data and expressly identifies anomaly detection as a machine-learning problem; see paragraph [0307]); and
f. in the processing center, in case of detected anomaly, executing the step of identifying the operational condition of the machine and fault classification using one or more machine learning techniques (see cloud-based machine learning that processes industrial sensor data to classify the data, recognize operating conditions, recognize patterns indicating faults, and predict faults; see paragraph [0308]).
Cella does not expressly teach collecting data from the electrical current and voltage signals of a rotating electrical machine with a data acquisition module in a coordinated rotating-machine monitoring arrangement in which both the operating current and voltage supplied to the machine are acquired and provided to the recited gateway and processing-center operations.
Parlos teaches collecting data from the electrical current and voltage signals of a rotating electrical machine with a data acquisition module. In particular, Parlos teaches monitoring the operating condition of rotating electromechanical machines using the operating currents and voltages supplied to or from the machines and measuring the current and voltage through PTs and CTs located at the switchgear bus supplying the machines (see paragraphs [0005] and [0006]). Parlos further teaches an embedded monitoring device that receives measured voltage and current time-series data and either determines the machine condition locally or transmits processed signals to a remote computing system for determining the machine condition (see paragraphs [0011] and [0012]).
It would have been obvious to one skilled in the art, prior to the effective filing date, to modify Cella by incorporating the collection of both operating-current and operating-voltage signals supplied to a rotating electrical machine as taught by Parlos and using those signals as inputs to Cella’s gateway and cloud-based processing arrangement, as doing so would provide inexpensive and scalable remote monitoring of rotating electrical machines because Parlos emphasizes in paragraph [0415] that current-and-voltage monitoring can be implemented inexpensively using existing current transformers and potential transformers in motor-control or switchgear centers, thereby making it feasible to monitor large numbers of motors remotely from one location. It further would have been obvious to perform Cella’s disclosed compression, encryption, and Internet-transfer operations at the gateway and Cella’s disclosed decoding, FFT, subsampling, feature extraction, anomaly detection, and fault-classification operations at the cloud processing center because See in paragraph [1401] that compressing the sensor data reduces the amount of transmitted data and network-bandwidth usage, encrypting the data permits secure transmission, and delivering the resulting data to a cloud server enables remote processing.
PNG
media_image1.png
1026
1348
media_image1.png
Greyscale
Regarding claim 2, Cella & Parlos discloses the method of claim 1, wherein Cella further discloses the data acquisition module is installed inside an electrical panel and collects electrical current and voltage signals from a rotating electrical machine using current transformers and branching or tap points on conductors installed next to the phase conductors inside the electrical panel (see [0483] power panels as local IoT endpoint devices, sensors attached to or integrated into monitored equipment [0486], and a monitoring device containing a data-acquisition circuit; Cella expressly identifies current and voltage sensors, ammeters, and voltmeters as sensor inputs. Under the broadest reasonable interpretation, the recited CT and conductor-tap arrangement constitutes current- and voltage-sensing elements operationally coupled to the machine’s electrical conductors; also see paragraphs [1154], and [1933]).
Regarding claim 3, Cella & Parlos discloses the method of claim 1, wherein Cella further discloses the step of detecting anomalies in the signals with one or more statistical techniques and one or more machine-learning techniques includes principal component analysis (PCA) and includes an autoencoder neural network (see [0782] a dimensionality-reduction algorithm comprising one or more of PCA and stacked autoencoders, and separately illustrates a streaming data-collection system containing an autoencoder neural network connected to an expert system; also see paragraph [1325]).
Regarding claim 4, Cella & Parlos discloses the method of claim 1, wherein Cella further discloses the step of identifying the machine’s operational condition and classifying a fault with one or more machine-learning techniques includes convolutional neural networks and one or more boosting algorithms based on decision trees (see decision-tree-based learning, gradient boosting, and AdaBoost, and further discloses a deep convolutional neural network connected to the streaming data-collection and expert systems; see paragraphs [0307] and [0783]).
Regarding claim 5, Cella & Parlos discloses the method of claim 1, wherein Cella further discloses obtaining validation from an operator regarding detected faults and inserting the received validation, together with newly collected data from the failing machine, into training of the machine-learning models (see paragraph [0785]; entries from an operator indicating a failure, fault, or service event, and iteratively improving pattern-recognition operations based on those entries and the machine conditions occurring before the known outcome; Cella further discloses training neural networks with sensor data and indicators of an outcome under human-operator supervision; see [0988]).
Regarding claim 6, Cella & Parlos discloses the method of claim 1, wherein Cella further discloses data transfer between the data acquisition module and the gateway device occurs remotely through a local wireless or wired communication network (see directing streaming and processed data from the DAQ instrument to a cloud-network facility through wired or wireless transmission and discloses a gateway linking client devices on a LAN to the Internet; see paragraphs [0403] and [1712]).
Regarding claim 7, Cella & Parlos discloses the method of claim 1, wherein Cella further discloses the rotating electrical machine is an induction electric motor, a generator, a pump, a fan, a conveyor belt, an agitator, a reducer, an elevator, a turbine, a compressor, or a gearbox (see [0232] induction motors, compressors, fans, belt-and-pulley systems, gearboxes, turbines, pumps, motors, rotors, and other rotating industrial machines; see paragraph [0323]; wherein the recited machines constitute alternative examples, disclosure of any one of the identified rotating-machine types satisfies the limitation).
Regarding claim 8, Cella & Parlos discloses the method of claim 1, wherein Cella further discloses the operational condition of machine failure includes wear see paragraphs [0898], scratches and bearing failures, bearing failure, eccentricities, broken rotor bars, shaft misalignment, shaft unbalance, shaft backlash, soft foot, overload, voltage transients, phase unbalance, harmonic distortion, Sigma currents, pump cavitation, pump clogging, corrosion of parts, resonance, seal-assembly failure, leakage, rotational looseness, structural looseness, or operator failure (under the broadest reasonable interpretation, “includes” introduces nonexclusive examples of detectable failure conditions and does not require the simultaneous presence of every listed failure; Cella expressly discloses out-of-balance machines, misalignment, resonance, bent shafts, rotor and stator faults, bearing failures, mechanical looseness, cavitation, excessive friction, fluid leakage, blockage, wear, overload, corrosion, seal failure, and other mechanical and electrical failure conditions; see [1150] & [1153]).
Regarding claim 9, See a system for monitoring the operational condition of rotating electrical machines and automatic detection of mechanical and electrical faults (see an industrial monitoring platform having analog sensors monitoring a rotating machine component and a data-acquisition and analysis circuit that determines the occurrence of an anomalous operating condition using an expert system and a neural network; see paragraph [0014]), comprising:
a. a data acquisition module for collecting electrical current and voltage signals and transferring the data of electrical current and voltage signals to the gateway device (See a local data collection system that obtains data from industrial machines, teaches data-acquisition sensors comprising current sensors and voltage sensors, and teaches local client nodes communicating collected data through a gateway; see paragraphs [0198] and [0483]);
b. a gateway device for compressing the electrical current and voltage data, encrypting the electrical current and voltage data, and transferring the electrical current and voltage data to the processing center (see a gateway connecting a local area network to the Internet and teaches a network-management arrangement that compresses sensor data, encrypts the sensor data, and delivers the resulting data to a central or cloud server; see paragraphs [1401] and [1712]); and
c. a processing center on a cloud computing platform (see a host processing system disposed in a cloud-computing environment and receiving data from a local data collection system through a network-data-transport system; see paragraph [0198]):
i. wherein the electrical current and voltage data is decoded (see decoding coded data at a receiving system to reconstruct the original information units; see paragraph [1768]);
ii. wherein FFT is performed (see performing frequency analysis of a signal using a digital Fast Fourier transform; see paragraph [0512]);
iii. wherein the electrical current and voltage data is subsampled in the time domain (See reducing the sampling frequency of a time-domain waveform and averaging adjacent time-domain sampling points; see paragraph [0256]);
iv. wherein attributes of the signals are extracted in the time and frequency domains (see extracting signal information and features using statistical operations, transformations, spectral estimation, modeling, analysis, and feature-extraction techniques; see paragraph [0306]);
v. wherein one or more statistical techniques and one or more machine learning techniques are implemented for anomaly detection in the electrical current and voltage signals (see applying mathematical and statistical techniques and machine-learning techniques to collected industrial sensor data and expressly identifies anomaly detection as a machine-learning problem; see paragraph [0307]); and
vi. wherein one or more machine learning techniques are implemented for identifying the operational condition of the machine and fault classification (see cloud-based machine learning that classifies industrial sensor data, recognizes machine operating conditions, recognizes patterns indicating the presence of faults, and predicts faults; see paragraph [0308]).
Cella does not expressly teach a data acquisition module for collecting electrical current and voltage signals of a rotating electrical machine in a coordinated system in which both the operating current and voltage supplied to the machine are acquired and provided through the gateway device to the cloud-based processing center.
Parlos teaches a data acquisition and monitoring device for collecting both electrical current and voltage signals associated with a rotating electrical machine. In particular, Parlos teaches monitoring rotating electromechanical machines based on the operating currents and voltages supplied to or from the machines and measuring the machine current and voltage through PTs and CTs at the switchgear bus supplying the machines (see paragraphs [0005] and [0006]). Parlos further teaches an embedded monitoring device that receives measured voltage and current time-series data, performs signal processing, and transmits the processed signals to a remote computing system that detects the machine condition (see paragraphs [0011] and [0012]).
It would have been obvious to one skilled in the art, prior to the effective filing date, to modify Cella’s system by incorporating Parlos’s data-acquisition arrangement for collecting both the operating-current and operating-voltage signals supplied to a rotating electrical machine and providing those signals to Cella’s gateway and cloud-based processing center, as doing so would provide inexpensive and scalable remote monitoring of rotating electrical machines because Parlos emphasizes in paragraph [0415] that current-and-voltage monitoring can be implemented inexpensively using existing current transformers and potential transformers in motor-control or switchgear centers, thereby making it feasible to monitor large numbers of motors remotely from one location.
Regarding claim 10, Cella & Parlos discloses the system of claim 9, wherein Cella further discloses the data acquisition module (see [0483]) is installed in the electrical panel and collects electrical current and voltage data from a rotating electrical machine using CTs and VTs installed next to the phase conductors supplying the rotating electrical machine (Cella discloses [0486], a power panel operating as an IoT endpoint, current and voltage sensors connected to a data-acquisition circuit, and ammeter and voltmeter sensor inputs attached to or integrated into monitored equipment. Under the broadest reasonable interpretation, CTs and VTs are respective current- and voltage-sensing devices operationally coupled to the electrical conductors supplying the monitored machine; also see paragraphs [1154], and [1933]).
Regarding claim 11, Cella & Parlos discloses the system of claim 9, wherein Cella further discloses the processing center is adapted to perform principal component analysis and an autoencoder neural network in the signal-anomaly-detection step using one or more statistical techniques and one or more machine-learning techniques (see [0782] PCA and stacked autoencoders as dimensionality-reduction algorithms that can be executed at a remote computing system, and an autoencoder neural network interfacing with an expert system; also see paragraph [1325]).
Regarding claim 12, Cella & Parlos discloses the system of claim 9, wherein Cella further discloses the processing center is adapted to apply convolutional neural networks and one or more boosting algorithms based on decision trees when identifying the machine’s operational condition and classifying a fault using one or more machine-learning techniques (see [0307] deep convolutional neural networks, decision-tree-based learning, gradient boosting, and AdaBoost; see paragraph [0783]).
Regarding claim 13, Cella & Parlos discloses the system of claim 9, wherein Cella further discloses the processing center is adapted to obtain validation from an operator regarding detected faults and insert the received validation, together with newly collected data from the failing machine, into training of the machine-learning models (see [0785] operator entries identifying faults or failures and iterative improvement of pattern recognition based on the entries and sensor conditions preceding the identified outcome; see paragraph [0988]).
Regarding claim 14, Cella & Parlos discloses the system of claim 9, wherein Cella further discloses the gateway device communicates remotely with the data acquisition module through a local wireless or wired communication network (see [0403] wired or wireless transmission from the DAQ instrument and a gateway connecting local client devices on a LAN to the Internet; also see paragraph and [1712]).
Regarding claim 15, Cella & Parlos discloses the system of claim 9, wherein Cella further discloses the rotating electrical machine is an induction electric motor, a generator, a pump, a fan, a conveyor belt, an agitator, a reducer, an elevator, a turbine, a compressor, or a gearbox (see induction motors, fans, compressors, belt systems, pumps, turbines, motors, and gearboxes; see paragraph [0323]).
Regarding claim 16, Cella & Parlos discloses the system of claim 9, wherein Cella further discloses the operational condition of machine failure includes wear, scratches and bearing failures (see [0898]), bearing failure, eccentricities, broken rotor bars, shaft misalignment, shaft unbalance, shaft backlash, soft foot, overload, voltage transients, phase unbalance, harmonic distortion, Sigma currents, pump cavitation, pump clogging, corrosion of parts, resonance, seal-assembly failure, leakage, rotational looseness, structural looseness, or operator failure (under the broadest reasonable interpretation, “includes” provides nonexclusive examples of detectable machine-failure conditions; Cella expressly discloses imbalance, misalignment, resonance, rotor and stator faults, bearing failures, mechanical looseness, cavitation, excessive friction, blockage, fluid leakage, wear, overload, corrosion, and seal failures; also see paragraphs and [1150]–[1153]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
U.S. 12,252,020 B2 to Zang discloses a method for monitoring and identifying sensor faults in an electric drive system of a vehicle includes collecting corresponding data using sensors in the electric drive system, inputting the collected data to an already-established sensor fault mode identification model, and determining whether a fault mode exists and a fault mode type based on the collected data using the sensor fault mode identification model. The method quickly determines the fault mode caused by a sensor fault in the electric drive system, and the fault mode type of the sensor fault.
U.S. 2024/0133954 A1 to Liu et al. disclose a fault detection system of eccentricity severity of an induction machine including a rotor and stator is provided. The fault detection system includes a sensor interface configured to acquire sensor signals from sensors arranged at predetermined positions of the induction machine, wherein the sensor signals are indicative of an eccentricity level of a rotor of the induction machine, a memory coupled with a processor. The memory stores training data sets and instructions implementing a learning-based fault detection method for the induction machine. The instructions include steps of generating an eccentricity feature matrix from the sensor signals, where in the sensor signals include load torque, rotor speed, vibration acceleration of the rotor, vibration speed of the rotor, and current spectral of the stator or the induction machine, determining an eccentricity level of the induction machine based on the eccentricity feature matrix using the learning-based fault detection method, wherein the learning-based fault detection method is configured to find the eccentricity level from learning-based eccentricity feature matrix data sets.
U.S. 2018/0374379 A1 to Nappa discloses a mechatronic training and simulation system and method of detecting and resolving complex control system errors in automation-driven process that replicates a scaled factory. The system provides student work stations that allow students to monitor, analyze and repair an automation-driven process. The automation-driven process includes at least one scaled model factory station simulator such as: a robot station, a warehouse station, a furnace processing station, and error checking color sorting station. A problem interjecting device to introduce errors to the automation-driven process through discrete I/O interfacing to interrupt process flow by breaking inputs and breaking outputs. Students at the student work stations, independently or concurrently, analyze and repair interruptions in automation-driven process through use of interface software and electrical measurement instruments. Students learn theoretical and practical hands on technical knowledge for debugging and troubleshooting programmable logic control systems and automation-driven mechanical systems.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TRUNG NGUYEN whose telephone number is (571)272-1966. The examiner can normally be reached on Mon- Friday 8AM - 4:00PM Eastern Time. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Huy Phan can be reached on 571-272-7924. 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.
Examiner: /Trung Q. Nguyen/- Art 2858
/GIOVANNI ASTACIO-OQUENDO/ Primary Examiner, Art Unit 2858 8/19/2026
Prosecution Insights