Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference (한국전기전자재료학회:학술대회논문집)
- 2004.05b
- /
- Pages.100-103
- /
- 2004
PD Source Classification of Model Specimens for GIS
GIS 모의결합의 부분방전원 분류
- Park, Sung-Hee (Chungbuk National University) ;
-
Lim, Kee-Joe
(Chungbuk National University) ;
- Kang, Seong-Hwa (Chungcheong University) ;
- Lee, Chang-Jun (LG industrial co.) ;
- Lee, Hee-Cheol (LG industrial co.)
- Published : 2004.05.21
Abstract
In this paper, BP learning algorithm is studied to apply as a PD source classification in GIS specimens. For occurred partial discharge, three defected models are made; floating particle, surface discharge of spacer, needle to plane. And PD data for discrimination were acquired from PD detector. And these data making use of a computer-aided discharge analyser, statistical and other discharge parameters is calculated to discrimination between different models of discharge sources. And also these parameter is applied to classify PD sources by neural networks. Neural Networks has good recognition rate for three PD sources.