Substation monitoring information feature extraction method and device

• Main Authors: ZHAO XILAN, YIN HONGWEI, LIN CHUNLONG, WANG DONGQING, HE YUJIAO, WANG JIA, ZHANG HONG, WANG BINBIN, SHI JIAOYANG, LIAN YUNZHEN, GAO FENG, WANG ZHILEI, SUN XUN, CHENG YU, YANG JIANMEI, SHI MINGRUI, SONG HONGWEI, ZHENG WENHUI, SUN XIAOTAO, FAN YUKUN, WANG GENG, GAI XIAOPING
• 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; ELECTRIC DIGITAL DATA PROCESSING; 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 extraction method and device, and the method comprises the steps: a data preprocessing step, which comprises the steps: processing an analog signal, and extracting the correlation features of analog data through digital signal processing; extracting warning information text keywords; performing extraction, cleaning and time synchronization preprocessing on the data; the data classification step comprises the steps of performing classification according to the association features of the preprocessed analog quantity data and the text keywords of the alarm information to form state features; and a time sequence feature extraction step: processing the state features obtained in the data classification step according to a time sequence relationship to form synchronous state features with time sequence information. According to the method, the basic features, the state features and the time sequence features of the transformer substati