# US 12,008,072 B2 · Control system and control method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,008,072 B2 - Document ID: US12008072B2 - Status: Granted - Kind: B2 - Application number: 17/278,664 - Filed: 2019-10-09 - Published: 2022-02-10 - Granted: 2024-06-11 - Earliest claimed: 2018-10-23 - Assignees: OMRON Corporation - Applicants: OMRON Corporation - Inventors: Takahiro Toku; Kota Miyamoto - Web page: https://patentgrep.com/patent/US12008072B2 ## CPC - G06F 18/2113: by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation - G05B 23/0221: {Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods} - G05B 23/024: {Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks} - G06F 18/213: Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods - G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting - G06F 18/2431: Multiple classes - G06N 20/00: Machine learning - H03M 7/6041: {Compression optimized for errors} - H03M 7/3059: {Digital compression and data reduction techniques where the original information is represented by a subset or similar information, e.g. lossy compression} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - H03M: CODING; DECODING; CODE CONVERSION IN GENERAL (using fluidic means F15C4/00; optical analogue/digital converters G02F7/00; coding, decoding or code conversion, specially adapted for particular applications, see the relevant subclasses, e.g. G01D, G01R, G06F, G06T, G09G, G10L, G11B, G11C, H04B, H04L, H04M, H04N; ciphering or deciphering for cryptography or other purposes involving the need for secrecy G09C) ## Abstract A control system includes: a generation unit that generates a dataset for each unit section; a feature extraction unit that generates feature quantity data on the basis of the dataset; and a score calculation unit that calculates a score indicating a degree of deviation of the feature quantity data from learning data, by referring to the learning data. The feature quantity data and the score are output as compression results of the dataset. The control system includes a restoration unit that selects pattern data corresponding to a class determined according to the score contained in the compression result, and after adjusting the pattern data using the feature quantity data contained in the compression results, restores the pattern data as a temporal change in the dataset corresponding to the compression results. ## Claims ### Claim 1 A control system comprising: a generation unit that generates a dataset comprising temporal changes in one or more input values for each unit section; a feature extraction unit that generates feature quantity data on the basis of the dataset; a score calculation unit that calculates a score indicating a degree of deviation of the feature quantity data from learning data, by referring to the learning data comprising feature quantity data labeled with a specific class, wherein the feature quantity data and the score are output as compression results of the dataset; and a restoration unit that selects pattern data corresponding to a class determined according to the score contained in the compression results by referring to pattern data for each class prepared in advance, and after adjusting the pattern data using the feature quantity data contained in the compression results, restores the pattern data as a temporal change in the dataset corresponding to the compression results. ### Claim 2 (depends on 1) The control system according to claim 1, wherein a plurality of the compression results are continuously output, and the restoration unit continuously restores the temporal change in the dataset from each of the compression results. ### Claim 3 (depends on 1) The control system according to claim 1, wherein the feature quantity data comprises an average and a standard deviation of the dataset, and the restoration unit restores the temporal change in the dataset by denormalizing the corresponding pattern data on the basis of the average and the standard deviation of the dataset. ### Claim 4 (depends on 1) The control system according to claim 1, further comprising a sampling unit that extracts a temporal change in a dataset corresponding to the compression result when the score comprised in the compression result exceeds a predetermined value. ### Claim 5 (depends on 4) The control system according to claim 4, wherein when the degree of deviation of the temporal change in the extracted dataset from the pattern data prepared in advance exceeds a predetermined value, the sampling unit adds the temporal change in the extracted dataset as the pattern data referred to by the restoration unit. ### Claim 6 (depends on 5) The control system according to claim 5, wherein in addition to the feature quantity data and the score, the pattern data added by the sampling unit is output as the compression result. ### Claim 7 (depends on 5) The control system according to claim 5, wherein the restoration unit restores the temporal change in the dataset by referring to the pattern data added by the sampling unit in addition to the pattern data prepared in advance. ### Claim 8 (depends on 1) The control system according to claim 1, further comprising a judgment unit that judges, on the basis of the score, whether or not an abnormality has occurred in an object to be monitored related to the one or more input values. ### Claim 9 (depends on 1) The control system according to claim 1, comprising: a control apparatus that controls an object to be controlled; and external apparatuses capable of communicating with the control apparatus, wherein the generation unit, the feature extraction unit, and the score calculation unit are arranged in the control apparatus, and the restoration unit is arranged in the external apparatus. ### Claim 10 A control method executed in a control system comprising a control apparatus for controlling an object to be controlled, comprising: a step of generating a dataset comprising temporal changes in one or more input values for each unit section; a step of generating feature quantity data on the basis of the dataset; a step of calculating a score indicating a degree of deviation of the feature quantity data from learning data, by referring to the learning data comprising feature quantity data labeled with a specific class, wherein the feature quantity data and the score are output as compression results of the dataset; and a step of selecting pattern data corresponding to a class determined according to the score contained in the compression result by referring to pattern data for each class prepared in advance, and after adjusting the pattern data using the feature quantity data contained in the compression results, restoring the pattern data as a temporal change in the dataset corresponding to the compression results.