Substation monitoring information feature selection method, storage medium and equipment

• Main Authors: ZHAO XILAN, CHEN XUAN, MA SICHAO, LIN CHUNLONG, WANG DONGQING, WANG MEIKUN, WANG BINBIN, MA LONG, SHI JIAOYANG, GAO FENG, GOU LIN, WANG WEIZHOU, SUN XUN, LIU HAICHAO, WANG XIA, YANG JIANMEI, ZHENG WENHUI, XIA CHANGMING, WANG LIXIANG, FAN YUKUN, ZHAO XIQUAN, GAI XIAOPING, LIU CHUNMING
• Format: Patent
• Language: Chinese; English
• Published: 15.03.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a transformer substation monitoring information feature selection method, which comprises the following steps of: constructing a target fault event set according to fault events reflected by transformer substation monitoring information; determining a data source range of the target fault event; forming an alternative feature set by the data source range; calculating the correlation between each alternative feature in the alternative feature set and the target fault event, the redundancy of the alternative feature and other features, the weight of the alternative feature based on the electrical distance, and the fuzzy weight of the alternative feature based on the information property; according to the correlation, the redundancy, the weight based on the electrical distance and the fuzzy weight based on the information property, calculating the weighted maximum correlation minimum redundancy value of the alternative feature corresponding to the target fault event, and performing sortin