Periodic operation component multi-element perception abnormal mode time sequence dependence mining method

• Main Authors: CUI GAOSHUN, ZHANG HAIZHU, ZENG WENQU, WANG SHUYING, DING GUOFU
• Format: Patent
• Language: Chinese; English
• Published: 02.06.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention relates to a periodic operation component multivariate perception abnormal mode time sequence dependence mining method. The method comprises the steps that S1, a component multivariate perception variable abnormal event capturing platform is constructed; s2, capturing time sequence data of a sensing variable abnormal mode, and constructing an abnormal time sequence database EventseqDB; s3, constructing a multi-element sensing abnormal mode time sequence database KDDSeqDB; and S4, carrying out multivariate perception abnormal mode time sequence dependence mining based on the improved PrefixSpan. According to the method, the time sequence causal relationship formed by faults in the operation and maintenance process of the component can be effectively mined by constructing the time sequence dependence model and algorithm of the multi-sensing variable sensing mode of the important component, and support is provided for preventive maintenance and design iterative optimization. 本发明涉及一种周期运行部件多元感知异常模式时序