A neural network based method for leakage current prediction of polymeric insulators

被引：32

作者：

Jahromi, AN ^{[1
]}

El-Hag, AH

Jayaram, SH

Cherney, EA

Sanaye-Pasand, M

Mohseni, H

机构：

[1] Univ Waterloo, Waterloo, ON N2L 3G1, Canada

[2] Univ Tehran, Tehran, Iran

来源：

IEEE TRANSACTIONS ON POWER DELIVERY | 2006年 / 21卷 / 01期

关键词：

leakage current; neural network; polymeric insulator; salt-fog test;

D O I：

10.1109/TPWRD.2005.858805

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This letter describes a neural network approach to the prediction of the leakage current (LC) on silicone rubber insulators exposed to salt-fog. The validity of the approach was examined by testing several insulators in a salt-fog chamber. Feed-forward back propagation was found as the best method among several training methods evaluated for the prediction of the LC. The predicted LC with this method has less than 12% error for the tested cases.

引用

页码：506 / 507

页数：2

共 5 条

[1]

AMRAH F, 2002, IEEE T POWER DELIVER, V17, P1063

[2]

DEMUTH H, 2003, MATLAB USER GUIDE VE

[3] Fundamental and low frequency harmonic components of leakage current as a diagnostic tool to study aging of RTV and HTV silicone rubber in salt-fog [J].