Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
The following NON-FINAL Office Action is in response to application 18/442,326 filed on 02/15/2024. This communication is the first action on the merits.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 02/29/2024 has been considered by the examiner.
Drawings
The drawings were received on 02/15/2023. These drawings are acceptable.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-20 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 1, 12, and 18 recites “subsampling the historic operating data to generate a plurality of clusters based on domain knowledge for the machine, each cluster representing data points from the historic operating data that are associated with an operating region for the machine, wherein the domain knowledge includes one or more model parameters associated with the machine”
Claim 9 recites “wherein the one or more model parameters are generated using the domain knowledge”.
Claim 10 recites “wherein the certain range of the values is predefined using the domain knowledge”.
The term “domain knowledge” renders the scope of the claims unclear because it is unclear what specifically constitutes “domain knowledge”, how such “domain knowledge” is determined, and what limitations, rules, parameters, or information qualify as “domain knowledge”. The claims fail to provide objective boundaries for determining the scope of the claimed “domain knowledge” and therefore one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
Specifically, it is unclear whether “domain knowledge” refers to machine parameters, threshold values, operating regions, explained variance parameters, priority tags, expert knowledge, training data, rules, operating constraints, or other information. Because the metes and bounds of the claimed “domain knowledge” cannot be determined with reasonable certainty, the claims are indefinite.
Dependent claims 2-11, 13-17, and 19-20 are rejected by virtue of their dependency.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more. A subject matter eligibility analysis is set forth below. See MPEP 2106.
Specifically, representative Claim 1 recites:
A computer-implemented method for detecting anomalies comprising:
obtaining, for a machine over a certain period of time, historic operating data for one or more parameters of the machine;
subsampling the historic operating data to generate a plurality of clusters based on domain knowledge for the machine, each cluster representing data points from the historic operating data that are associated with an operating region for the machine, wherein the domain knowledge includes one or more model parameters associated with the machine;
generating a model file that includes the plurality of clusters of the data points and the one or more model parameters;
receiving test data from the machine, the test data corresponding to current data points for the machine;
calculating, to the test data, a number of nearest neighbors from the plurality of clusters of the model file using an algorithm;
calculating a distance of the test data from the number of nearest neighbors; and
executing an action based on comparing the distance to a threshold value.
The claim limitations in the abstract idea have been highlighted in bold above; the remaining limitations are “additional elements.”
Claim 12 and Claim 16 comprise similar limitations of the abstract idea and perform the method of Claim 1.
Under Step 1 of the analysis, claim 1 belongs to a statutory category, namely it is a method claim. Likewise, claim 12 is a system claim, and claim 18 is a non-transitory computer-readable medium claim.
Under Step 2A, prong 1: This part of the eligibility analysis evaluates whether the claim recites a judicial exception. As explained in MPEP 2106.04, subsection II, a claim “recites” a judicial exception when the judicial exception is “set forth” or “described” in the claim.
In the instant case, claim 1 is found to recite at least one judicial exception (i.e. abstract idea), that being a Mental Process and a Mathematical Concept. This can be seen in the claim limitations of “obtaining, for a machine over a certain period of time, historic operating data for one or more parameters of the machine”, “subsampling the historic operating data to generate a plurality of clusters based on domain knowledge for the machine, each cluster representing data points from the historic operating data that are associated with an operating region for the machine, wherein the domain knowledge includes one or more model parameters associated with the machine”, “generating a model file that includes the plurality of clusters of the data points and the one or more model parameters, “calculating, to the test data, a number of nearest neighbors from the plurality of clusters of the model file using an algorithm”, “calculating a distance of the test data from the number of nearest neighbors” and “executing an action based on comparing the distance to a threshold value” which is the judicial exception of a mental process because these limitations are merely data observations, evaluations, and/or judgements in order to analyze operational data using mathematical relationships, statistical modeling, clustering techniques, nearest-neighbor analysis, and distance calculation to identify anomalies and is capable of being performed mentally and/or with the aid of pen and paper. Additionally, the aforementioned limitations recite mathematical calculations, e.g. see Spec. [0031]-[0046] describing the use of mathematical and statistical techniques to analyze operation data and identify anomalies.
Similar limitations comprise the abstract ideas of Claim 12 and Claim 18.
Step 2A, prong 2 of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception(s) into a practical application of the exception. This evaluation is performed by (a) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (b) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application.
In addition to the abstract ideas recited in claim 1, the claimed method recites additional elements including “A computer-implemented method for detecting anomalies”, “generating a model file that includes the plurality of clusters of the data points and the one or more model parameters”, “receiving test data from the machine, the test data corresponding to current data points for the machine”, and “executing an action based on comparing the distance to a threshold value” however these elements are found to be data gathering and output steps, which are recited at a high level of generality, and thus merely amount to “insignificant extra-solution” activity(ies). See MPEP 2106.05(g) “Insignificant Extra-Solution Activity,”. Furthermore, the claim recites that the steps, e.g. “calculating”, “receiving”, or “generating”, are performed by the computer however this is found to be equivalent to adding the words “apply it” and mere instructions to apply a judicial exception on a general purpose computer does not integrate the abstract idea into a practical application. See MPEP 2106.05(f).
The generic data gathering, processing, and output steps, are recited at such a high level of generality that it represents no more than mere instructions to apply the judicial exceptions on a computer. It can also be viewed as nothing more than an attempt to generally link the use of the judicial exceptions to the technological environment of a computer. Noting MPEP 2106.04(d)(I): “It is notable that mere physicality or tangibility of an additional element or elements is not a relevant consideration in Step 2A Prong Two. As the Supreme Court explained in Alice Corp., mere physical or tangible implementation of an exception does not guarantee eligibility. Alice Corp. Pty. Ltd. v. CLS Bank Int’l, 573 U.S. 208, 224, 110 USPQ2d 1976, 1983-84 (2014) ("The fact that a computer ‘necessarily exist[s] in the physical, rather than purely conceptual, realm,’ is beside the point")”.
Thus, under Step 2A, prong 2 of the analysis, even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application and the claim is directed to the judicial exception. No specific practical application is associated with the claimed system. For instance, nothing is done with the results of clustering, nearest-neighbor analysis, feature-space transformation, Mahalanobis distance, and threshold comparisons other than identifying anomalies and optionally generating generic warnings or action using conventional computer components.
Under Step 2B, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements, as described above with respect to Step 2A Prong 2, merely amount to a general purpose computer system that attempts to apply the abstract idea in a technological environment, limiting the abstract idea to a particular field of use, and/or merely performs insignificant extra-solution activit(ies) (claims 1, 12 and 18). Such insignificant extra-solution activity, e.g. data gathering and output, when re-evaluated under Step 2B is further found to be well-understood, routine, and conventional as evidenced by MPEP 2106.05(d)(II) (describing conventional activities that include transmitting and receiving data over a network, electronic recordkeeping, storing and retrieving information from memory, and electronically scanning or extracting data from a physical document).
Therefore, similarly the combination and arrangement of the above identified additional elements when analyzed under Step 2B also fails to necessitate a conclusion that claim 1, as well as claim 12, and claim 18, amount to significantly more than the abstract idea.
With regards to the dependent claims, claims 2-11, 13-17 and 19-20, merely further expand upon the algorithm/abstract idea and do not set forth further additional elements that integrate the recited abstract idea into a practical application or amount to significantly more. Therefore, these claims are found ineligible for the reasons described for claims 1, 12 and 18. Specifically:
With respect to dependent claims 2-4, 13-15, and 19 specifically, the claims further recite generating alarms, transmitting alarms, suppressing alarms, and transmitting instructions to cease operation of a machine. However, these limitations merely amount to insignificant post-solution activity, including outputting results of the abstract data analysis and communicating the results over generic computer interfaces and networks. The recited alarm generation, warning transmission, and operational control instructions merely use generic computer functionality to convey the results of the abstract anomaly analysis and do not improve the functioning of a computer or another technology. Accordingly, these limitations fail to integrate the abstract idea into a practical application or amount to significantly more. See MPEP 2106.05(g).
With respect to dependent claims 5-8, 16-17, and 20 specifically, the claims further recite principal component analysis, feature space transformation, Mahalanobis distance calculations, k-nearest neighbor, and clustering algorithms. These limitations are directed to mathematical relationships, statistical modeling and mathematical calculations used to analyze operational data and identify anomalies. Such limitations constitute mathematical concepts and mental processes because they involve calculations, evaluations, and analysis of data to derive additional information. These limitations merely apply mathematical concepts using generic computer implementation and therefore fail to integrate the abstract idea into a practical application or amount to significantly more. See MPEP 2106.05(f).
With respect to dependent claims 9-11 specifically, the claims further recite explained variance, priority tags, threshold values, operating regions, and parameter ranges associated with machine operation. However, these limitations merely amount to additional data-analysis rules, threshold tuning parameters, and organizing or evaluating information for use in the abstract anomaly-detection analysis. The recited merely refine the mathematical model and data analysis process and do not improve the functioning of the computer or another technology. Accordingly, these limitations fail to integrate the abstract idea into a practical application or amount to significantly more. See MPEP 2106.05 (f)(g).
Accordingly, for the reasons above and those discussed in relation to independent claims 1, 12, and 18, the dependent claims are insufficient to integrate the claimed abstract idea into a practical application or amount to significantly more.
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, 4-8, 12, 15-18, and 20 are rejected under 35 U.S.C. 102(a)(1)\(a)(2) as being anticipated by US 20220107630 A1, Zope et al. (hereinafter Zope).
Regarding Claim 1, 12, and 18, Zope discloses a computer-implemented method for detecting anomalies (Zope, [0009] the processor-implemented method comprising determining at least one from the one or more regimes of operation unmatched regime of operation based on comparison with at least one past regime of operation stored in a regime database and detecting presence of anomalies in the at least one unidentified regime of operation using a plurality of data-driven anomaly detection models) comprising:
obtaining, for a machine (Zope, [0052] Initially, at the step (502), a plurality of data is received from one or more databases of a plurality of industrial assets at a pre-determined frequency. The plurality of data comprises real-time and non-real-time data. The one or more databases include operations database, laboratory database, maintenance database and an environment database) over a certain period of time, historic operating data for one or more parameters of the machine (Zope, [0039] if the regime similarity score obtained for the regime sequence of the segment and any of the pre-existing regime sequences in historical regime database is greater than a predefined threshold, the regime for the time segment matches with one of the pre-existing regimes of operation. The time segment is assigned the regime ID corresponding to the pre-existing regimes of operation. Regime sequences in the historical regime database are obtained by applying regime identification on historic data segments. After applying regime sequences segments with similar regime sequences are grouped together and percentage of sequences in each group is calculated);
subsampling the historic operating data to generate a plurality of clusters based on domain knowledge for the machine (Zope, [0036] the regime identification module (120) of the system (100) is configured to identify one or more regimes of operation of the plurality of industrial assets from the integrated data using a hierarchical clustering on segmented data. Herein, the regime identification module (120) obtains one or more regime sequences from the integrated data to compute a regime similarity score (RSS) corresponding to each of the one or more historical regime sequences. Further, the regime identification module (120) may compare the computed regime similarity score with a predefined threshold of regime similarity score to identify one or more regimes of operation of the plurality of industrial assets), each cluster representing data points from the historic operating data that are associated with an operating region for the machine (Zope, [0036] obtains one or more regime sequences from the integrated data to compute a regime similarity score (RSS) corresponding to each of the one or more historical regime sequences [0040] the grouping module (122) of the system (100) configured to group the plurality of industrial assets into one or more groups based on the regime IDs identified for one or more regimes of operation [0056] identifying one or more regimes of operation of the plurality of industrial assets from the integrated data using time series hierarchical clustering on segmented data. The hierarchical clustering comprising obtaining one or more regime sequences from the integrated data, computing a regime similarity score corresponding to each of the one or more regime sequences, comparing the computed regime similarity score with a predefined threshold of regime similarity score to identify one or more regimes of operation of the plurality of industrial assets), wherein the domain knowledge includes one or more model parameters associated with the machine (Zope, [0045] the process optimization is carried out to identify the optimum operating decisions to meet operations and/or maintenance objectives of the industrial assets within pre-determined process, equipment, and operating constraints. Operations objectives can be maximizing the output, quality, efficiency, etc. or minimizing the energy consumption, emissions, cost of operation, cost of maintenance, etc. Predictive models required for objective and constraint functions, lower and upper bounds of manipulated variables, and objective and constraint functions for each regime are stored in the optimization database. The process optimization module (130) selects prediction models, manipulated variables and their bounds and constraints that are suitable for each identified regime and grouped industrial assets from the optimization database and performs optimization to identify the optimized values for manipulated variables (MVs) for the given set of objectives and constraints [0048] Response variables include key process parameters in process plants and can be one or more of productivity, yield, cycle time, energy consumption, waste generation, emissions, quality parameters, condition of equipment, availability, mean time between failures, number of unplanned shutdowns, cost of operation, cost of maintenance, or a weighted combination of the above that is indicative of the condition of the plant, process and/or equipment. The predictions from various models aid the plant operator or engineer to take informed decisions concerning the operation of the plant, to keep a check on possible anomalies, to classify the state/health of the plant, to identify the root cause of detected anomalies, to estimate remaining useful life of various processes or equipment, and to optimize the operation in order to achieve desired levels of key process parameters);
generating a model file that includes the plurality of clusters of the data points and the one or more model parameters (Zope, [0042] one or more regimes of operation is less than predefined threshold and the data segment is not reported as anomaly by the diagnosis module (124), then regime sequence obtained for this segment is added as new regime in the Regime database [0044] the adaptive learning module (128) of the system (100) is configured to re-tune one or more predictive models according to the unmatched and non-anomalous regime of operations [0047] the data-driven models also include statistical, machine learning or deep learning based one-class or multi-class classification, scoring or diagnosis models such as principal component analysis, Mahalanobis distance, isolation forest, random forest classifiers, one-class support vector machine, artificial neural networks and its variants, elliptic envelope and auto-encoders (e.g. dense auto-encoders, LSTM auto-encoders, CNN auto-encoders) [0071] one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein);
receiving test data from the machine, the test data corresponding to current data points for the machine (Zope, [0031] the input/output interface (106) is configured to receive real-time and non-real-time data from various databases at a pre-determined frequency (e.g. 1/second, 1/minute, 1/hour, etc.) where the frequency is configurable by the user. Real-time data includes operations data and environment data. Operations data is recorded by sensors in the industrial asset and includes temperatures, pressures, flow rates and vibrations from processes and equipment in the units of the industrial asset);
calculating, to the test data, a number of nearest neighbors from the plurality of clusters of the model file using an algorithm (Zope, [0046] k-nearest neighbors regression [0039] After the regime sequences for each segment is obtained, a regime similarity score (RSS) is calculated to check if similar regime sequences are available in a historical regime database. The RSS may be calculated using weighted distance between obtained regime sequence of the segment and regime sequences available in database. Distance can be Euclidean, cityblock, cosine, euclidean, I1, I2, manhattan, braycurtis, canberra, chebyshev, correlation, dice, hamming, jaccard, kulsinski, ‘mahalanobis’, minkowski, rogerstanimoto, russellrao, seuclidean, sokalmichener, sokalsneath, sqeuclidean, yule; k-nearest algorithm is applied to the clustered variables to identify the nearest neighbors for the test data );
calculating a distance of the test data from the number of nearest neighbors (Zope, [0038] It would be appreciated that a set of clusters for variables is obtained by cutting the dendrogram perpendicular to the distance axis at a predefined height. After cutting the dendrogram, one or more clusters of variables are obtained and herein each variable within each of the one or more clusters is assigned a unique number and the regime sequence for each segment is obtained, [0039] After the regime sequences for each segment is obtained, a regime similarity score (RSS) is calculated to check if similar regime sequences are available in a historical regime database. The RSS may be calculated using weighted distance between obtained regime sequence of the segment and regime sequences available in database. Distance can be Euclidean, cityblock, cosine, euclidean, I1, I2, manhattan, braycurtis, canberra, chebyshev, correlation, dice, hamming, jaccard, kulsinski, ‘mahalanobis’, minkowski, rogerstanimoto, russellrao, seuclidean, sokalmichener, sokalsneath, sqeuclidean, yule. ); and
executing an action based on comparing the distance to a threshold value (Zope, [0059] detecting presence of one or more anomalies in the unmatched regime of operation using a plurality of data-driven anomaly detection models and identifying at least one cause of the detected one or more anomalies in the unmatched regime of operation of the plurality of assets using a plurality of data-driven anomaly diagnosis models [0061] estimating a remaining useful life (RUL) based on the identified cause of the anomaly to provide early warning of failure of one or more components in one or more assets).
Regarding Claim 4 and 15, Zope discloses the computer-implemented method according to claim 1, wherein the action includes suppressing an alarm for transmission to a computer device associated with the machine when the distance does not exceed the threshold value (Zope, [0039] After the regime sequences for each segment is obtained, a regime similarity score (RSS) is calculated to check if similar regime sequences are available in a historical regime database. The RSS may be calculated using weighted distance between obtained regime sequence of the segment and regime sequences available in database. Distance can be Euclidean, cityblock, cosine, euclidean, I1, I2, manhattan, braycurtis, canberra, chebyshev, correlation, dice, hamming, jaccard, kulsinski, ‘mahalanobis’, minkowski, rogerstanimoto, russellrao, seuclidean, sokalmichener, sokalsneath, sqeuclidean, yule [0039] Regime sequences with percentage higher than particular threshold are added in regime database. Prediction models are retuned for new identified regime. Sequences with percentage lower than threshold are sent to Anomaly detection and diagnosis module and added in ADD database if anomaly 0042] wherein the RSS of the one or more regimes of operation is less than predefined threshold and the data segment is not reported as anomaly by the diagnosis module).
Regarding Claim 5, 16, and 20, Zope discloses the computer-implemented method according to claim 1, wherein generating the model file includes applying a principal component analysis (PCA) algorithm using the plurality of clusters of the data points to transform the data points to a feature space (Zope, [0041] the diagnosis module (124) of the system (100) configured to detect anomaly in the unmatched regime of operation and a diagnosis is carried out to identify the root cause for the fault and the sensor contributing to anomalies. Statistical and Deep Learning techniques are used for Anomaly Detection and Diagnosis. Some multivariate statistical techniques are Principal Component Analysis, One-Class Support Vector Machine, Isolation Forest, Local Outlier Factor, Mahalanobis Distance, Elliptic Envelope, and deep learning techniques are LSTM Autoencoder, Dense Autoencoder and Convolutional Autoencoder etc).
Regarding Claim 6 and 17, Zope discloses the computer-implemented method according to claim 5, wherein calculating the distance of the test data from the number of nearest neighbors includes applying the PCA algorithm using the test data to transform the test data to the feature space (Zope, [0032] the pre-processing module (114) of the system (100) is configured to perform pre-processing of the real-time and non-real-time data received from multiple databases of the industrial manufacturing plant. Pre-processing involves removal of redundant data, unification of sampling frequency, filtering of data, outlier identification & removal, imputation of missing data, synchronization of data by incorporating appropriate lags, and integration of variables from various data sources [0038] one or more clusters of variables are obtained and herein each variable within each of the one or more clusters is assigned a unique number and the regime sequence for each segment is obtained [0046] It would be appreciated that the data-driven models include models built using statistical, machine learning or deep learning techniques such as variants of regression (multiple linear regression, stepwise regression, forward regression, backward regression, partial least squares regression, principal component regression, Gaussian process regression, polynomial regression, etc.)).
Regarding Claim 7, Zope discloses the computer-implemented method according to claim 1, wherein calculating the distance of the test data from the number of nearest neighbors includes using a Mahalanobis distance (Zope, [0039] Distance can be Euclidean, cityblock, cosine, euclidean, I1, I2, manhattan, braycurtis, canberra, chebyshev, correlation, dice, hamming, jaccard, kulsinski, ‘mahalanobis’, minkowski, rogerstanimoto, russellrao, seuclidean, sokalmichener, sokalsneath, sqeuclidean, yule)
Regarding Claim 8, Zope discloses the computer-implemented method according to claim 1, wherein the algorithm is a k-nearest neighbors (KNN) algorithm (Zope, [0046] data-driven models include models built using statistical, machine learning or deep learning techniques such as variants of regression (multiple linear regression, stepwise regression, forward regression, backward regression, partial least squares regression, principal component regression, Gaussian process regression, polynomial regression, etc.), decision tree and its variants (random forest, bagging, boosting, bootstrapping), support vector regression, k-nearest neighbors regression, spline fitting or its variants (e.g. multi adaptive regression splines), artificial neural networks and it variants (multi-layer perceptron, recurrent neural networks & its variants e.g. long short term memory networks, and convolutional neural networks) and time series regression models)
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.
Claims 2-3, 10-11, 13-14, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over US 20220107630 A1, Zope et al. (hereinafter Zope) in view of US 20180191758 A1, ABBASZADEH et al. (hereinafter Abbaszadeh).
Regarding Claim 2, 13, and 19, Zope in view of Abbaszadeh teaches the computer-implemented method according to claim 1, wherein the action includes generating an alarm (Abbaszadeh, [0032] At S240, the system may automatically transmit a threat alert signal (e.g., a notification message, etc.) based on results of the comparisons performed at S230.) and transmitting an alarm to a computer device associated with the machine when the distance exceeds the threshold value (Abbaszadeh, [0070] [0070] The selected cluster-based decision boundary can then be used to perform anomaly detection at S1350 and a current system status may be generated and/or transmitted at S1360 (e.g., indicating that the industrial asset is currently experiencing “normal” or “threatened” operation))
Before the effective filing date of the claimed invention, It would have been obvious to one of ordinary skill in the art to combine Zope and Abbaszadeh teachings because Abbaszadeh teaches generating and transmitting an alarm based on detection of anomalous operating conditions, while Zope teaches anomaly detection for industrial assets. One of ordinary skill in the art would have been motivated to integrate Abbaszadeh’s alarm generation and notification techniques into Zope’s anomaly detection system in order to automatically notify a user or associated computing device when an anomalous operating condition is detected, therefore improving the monitoring and fault system response.
Regarding Claim 3 and 14, Zope in view of Abbaszadeh teaches the computer-implemented method according to claim 1, wherein the action includes transmitting instructions to cease operation of the machine when the distance exceeds the threshold value (Abbaszadeh, [0032] At S240, the system may automatically transmit a threat alert signal (e.g., a notification message, etc.) based on results of the comparisons performed at S230. The threat might be associated with, for example, an actuator attack, a controller attack, a monitoring node attack, a plant state attack, spoofing, financial damage, unit availability, a unit trip, a loss of unit life, and/or asset damage requiring at least one new part. According to some embodiments, one or more response actions may be performed when a threat alert signal is transmitted. For example, the system might automatically shut down all or a portion of the industrial asset control system (e.g., to let the detected potential cyber-attack be further investigated). As other examples, one or more parameters might be automatically modified, a software application might be automatically triggered to capture data and/or isolate possible causes, etc).
Before the effective filing date of the claimed invention, It would have been obvious to one of ordinary skill in the art to combine Zope and Abbaszadeh teachings because Abbaszadeh teaches automatically shutting down all or a portion of a control system in response to a detected threat, while Zope teaches detecting anomalous operating conductions within industrial systems. A person of ordinary skill in the art would have been motivated to integrate Abbaszadeh’s automatic shutdown functionality into Zope’s anomaly detection system in order to automatically cease operation of a machine upon detection of an anomalous condition, thereby protecting industrial equipment and preventing damage or unsafe operation.
Regarding Claim 10, Zope in view of Abbaszadeh teaches the computer-implemented method according to claim 1, wherein each operating region of the operating regions (Abbaszadeh, [0060] By way of example, FIG. 10 illustrates 1000 clustered data in a two dimensional feature space in accordance with some embodiments. In particular, the two dimensional feature space is defined by operational characteristics w1 and w2. A set of cluster one data (represented by “+” icons) and a set of cluster two data (represented by “x” icons) are displayed in the space. Further, a centroid location for cluster one 1010 and a centroid location for cluster two 1020 may be computed and located in the two dimensional space as illustrated in FIG. 10) corresponds to a certain range of values for a parameter of the one or more parameters of the machine (Abbaszadeh, [0064] In general, the system may create a hypersphere around the normal operating points and, as a result, what is outside of that defined region might be considered abnormal (or “threatened”). That is, based on the data type(s) in each cluster, a cluster-based decision boundary may constructed for each data cluster as follows: [0065] For mixed-data clusters (containing both normal and attack training data) a supervised learning method (two-class) is used; [0066] For normal only (or attack only) clusters, a semi-supervised learning (one-class) may be used. The semi-supervised learning model might be, for example, a one-class Support Vector Machine (“SVM”) process, a K-Nearest Neighbor (“KNN”) algorithm, or any other semi-supervised learning technique. [0071] embodiments described herein may provide for the creation of decision boundaries when only one-class of data is available (using semi-supervised techniques). This will facilitate generation of boundaries using legacy asset data which might only include normal data (that is, the historical data for an industrial asset might not contain any attack data). The definition of an appropriate boundary might be performed in view of, for example, a Receiver Operating Characteristic (“ROC”), true positives, false positives, true negatives, false negatives, an Area Under Curve (“AUC”) value, etc.)
Before the effective filing date of the claimed invention, It would have been obvious to one of ordinary skill in the art to combine Zope and Abbaszadeh teachings because Abbaszadeh teaches defining operating regions using cluster based decision boundaries corresponding to ranges of operating characteristics, while Zope teaches identifying regimes of operation based on process parameter values. A person of ordinary skill in the art would have been motivated to integrate Abbaszadeh’s cluster operating regions into Zope’s optimization system in order to improve classification of machine operating states and anomaly detection using predefined parameter ranges.
Regarding Claim 11, Zope in view of Abbaszadeh teaches the computer-implemented method according to claim 1, wherein the threshold value is based at least in part on at least one of the machine, the operating region, or a priority tag parameter (Abbaszadeh, [0031] At S230, each generated current monitoring node feature vector may be compared to a corresponding decision boundary (e.g., a linear boundary, non-linear boundary, multi-dimensional boundary, etc.) for that monitoring node, the decision boundary separating a normal state from an abnormal state for that monitoring node. According to some embodiments, at least one monitoring node is associated with a plurality of multi-dimensional decision boundaries and the comparison at S230 is performed in connection with each of those boundaries).
Before the effective filing date of the claimed invention, It would have been obvious to one of ordinary skill in the art to combine Zope and Abbaszadeh teachings because Abbaszadeh teaches selecting decision boundaries that are specific to a monitoring node and its operating conditions, while Zope teaches identifying operating regimes for industrial assets. A person of ordinary skill in the art would have been motivated to integrate Abbaszadeh’s operating boundaries into Zope’s regime system so that threshold values are determined based on the operating region of the machine, thereby improving the accuracy and reliability of anomaly detection.
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.
Claims 9 are rejected under 35 U.S.C. 103 as being unpatentable over US 20220107630 A1, Zope et al. (hereinafter Zope) in view of US 20250259077 A1, KATKOORI et al. (hereinafter Katkoori).
Regarding Claim 9, Zope discloses the computer-implemented method according to claim 1, wherein the one or more model parameters include a priority tag (Zope, [0045] the process optimization module (130) of the system (100) is configured to optimize a plurality of key performance parameters of each group of the plurality of industrial assets. Herein, the process optimization is carried out to identify the optimum operating decisions to meet operations and/or maintenance objectives of the industrial assets within pre-determined process, equipment, and operating constraints. Operations objectives can be maximizing the output, quality, efficiency, etc. or minimizing the energy consumption, emissions, cost of operation, cost of maintenance, etc), a threshold (Zope, [0056] computing a regime similarity score corresponding to each of the one or more regime sequences, comparing the computed regime similarity score with a predefined threshold of regime similarity score to identify one or more regimes of operation of the plurality of industrial assets) and a number of neighbors (Zope, [0046] k-nearest neighbors regression), wherein the one or more model parameters are generated using the domain knowledge (Zope, [0050] In another embodiment illustrating creation of an adaptive learning knowledge base. The first set of data (operations data, laboratory data, environment data, maintenance data, soft-sensed data estimated using physics-driven or data-driven soft sensors, etc.) from multiple industrial assets of similar nature and function located in the same geographical location or at multiple geographical locations is used for performing regime identification for each of the plurality of industrial assets and regime-based process optimization for groups of industrial assets. The first set of data residing in multiple databases in the respective industrial assets can be brought to a common processor via a data communication network).
Zope does not disclose an explained variance
However, Katkoori teaches an explained variance (Katkoori, [0032] process 200 may determine the number of retained components dynamically based on an explained variance threshold, ensuring that only components contributing significantly to the variance of the data are retained while discarding lower-variance components, The specific PCA hyperparameters that may be considered can include: parameters defining the number of principal components to retain, the explained variance threshold for selecting components dynamically, whether to apply whitening to normalize feature variance, the choice of solver (e.g., full SVD, randomized SVD, or eigenvalue decomposition), batch size for Incremental PCA, and the kernel type for Kernel PCA (e.g., linear, polynomial, or RBF kernel))
Before the effective filing date of the claimed invention, It would have been obvious to one of ordinary skill in the art to combine Zope and Katkoori teachings because Katkoori teaches selecting principal components using an explained variance threshold to retain components that contribute significantly to the variance of the data while reducing dimensionality and computation complexity, while Zope teaches generating model parameters for industrial asset analysis using clustering and nearest neighbor techniques. A person of ordinary skill in the art would have been motivate to integrate Katkoori’s explained variance criteria into Zope’s data processing pipeline to improve feature selection, reduce redundant information and improve efficiency and accuracy of the generated model parameters.
Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant’s disclose:
-US 20230195715 A1, describing systems and methods for detecting anomalies in datasets using clustering algorithms, nearest-neighbor analysis, variance analysis, and anomaly remediation techniques for identifying anomalies in data.
-US 20180320658 A1, describing systems and methods for predicting abnormal events in industrial machines using clustered operational data, historical and current operating data comparisons, threshold-based anomaly analysis, and predictive operational control of industrial assets.
-US 20180191758 A1, describing systems and methods for generating cluster-based decisions boundaries using feature-space analysis, K-means clustering, nearest neighbor classification, and threshold based anomaly detection for industrial asset systems.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to IBRAHIM NAGI SHOHATEE whose telephone number is (571) 272-6612. The examiner can normally be reached 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, Shelby Turner can be reached at (571) 272-6334. 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.
/IBRAHIM NAGI SHOHATEE/Examiner, Art Unit 2857
/SHELBY A TURNER/Supervisory Patent Examiner, Art Unit 2857
Prosecution Insights