GIS internal insulation discharge type multispectral feature analysis method and system

The invention provides a GIS internal insulation discharge type multispectral characteristic analysis method and system, and the method comprises the steps: carrying out a sealed gas chamber experiment, filling a gas chamber with SF6 gas, simulating the internal environment of a GIS, carrying out th...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: SHEN QING, WANG PENG, CHEN XUE, LI QIYUE, XIE CHENG, LIU XIANG, YAO HAN, GUO ZHENYU, DONG XIANGYU, HUANG YONGSHENG, WAN ZIHAO, CHEN MINGYANG, ZHANG FANGWEI, MA HUAN, LI WEITAO, ZHANG QIAN, LI YANDONG, GAO HONGQIANG, XIA YOUSEN, ZHANG JIE, WANG TAIPING, ZHANG BIN, SUN WEI, HU KUN, LI SHUXIN, FU QINGTAI, DING FAN, ZHANG XUEYOU, ZHAO JULONG
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention provides a GIS internal insulation discharge type multispectral characteristic analysis method and system, and the method comprises the steps: carrying out a sealed gas chamber experiment, filling a gas chamber with SF6 gas, simulating the internal environment of a GIS, carrying out the discharge in different modes, simulating different discharge faults caused by the insulation defect of the GIS, employing a spectrograph, and carrying out the analysis of the multispectral characteristics of the GIS internal insulation discharge type. Collecting and recording the ultraviolet spectrum, the visible spectrum and the infrared spectrum; data mining: carrying out normalization processing on the data, identifying peak value characteristics in the spectral data through a segmentation clustering algorithm, and removing interference on the spectral data caused by discharge duration; and establishing a discharge type identification model by using a convolutional neural network, inputting the collected spect