Processing model construction method and processing method for monitoring data of extra-high voltage transformer

The invention discloses a processing model construction method and a processing method for monitoring data of an extra-high voltage transformer. The processing model construction method comprises the following steps: acquiring historical monitoring data of the extra-high voltage transformer; preproc...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	GUI FEIFEI, ZHENG ZHIWEN, YU LEI, CUI XIAOHONG, ZHANG FAN, ZHAO YUFANG, HUANG ZHIYONG, ZOU YIN, XIONG PENG, HE HONGTAI, ZHANG YU, WANG YUEXIANG, YU GUOHUA
Format:	Patent
Sprache:	chi ; eng
Schlagworte:	ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVEREDIN A SINGLE OTHER SUBCLASS CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES ELECTRIC DIGITAL DATA PROCESSING MEASURING MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR PHYSICS SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR TARIFF METERING APPARATUS TESTING
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	The invention discloses a processing model construction method and a processing method for monitoring data of an extra-high voltage transformer. The processing model construction method comprises the following steps: acquiring historical monitoring data of the extra-high voltage transformer; preprocessing the historical monitoring data; performing abnormal point detection on the preprocessed historical monitoring data by using an abnormal point detection algorithm; based on the preprocessed historical monitoring data and the detection result, a random forest processing model is constructed, the random forest processing model is used for processing to-be-processed monitoring data of the extra-high voltage transformer and outputting a processing result, and the processing result represents distribution characteristics of the to-be-processed monitoring data; the distribution characteristic is used for determining a storage mode of the to-be-processed monitoring data in the data warehouse. According to the method