Title :
A neural network based method for leakage current prediction of polymeric insulators
Author :
Jahromi, Ali Naderian ; El-Hag, Ayman H. ; Jayaram, Shesha H. ; Cherney, Edward A. ; Sanaye-Pasand, M. ; Mohseni, Hosein
Author_Institution :
Univ. of Waterloo, Ont., Canada
Abstract :
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.
Keywords :
backpropagation; feedforward neural nets; leakage currents; polymer insulators; power engineering computing; silicone rubber; feedforward back propagation; leakage current prediction; neural network; polymeric insulators; salt-fog chamber; silicone rubber insulators; training methods; Aging; Degradation; Feedforward systems; Insulation life; Insulator testing; Leakage current; Neural networks; Plastic insulation; Polymers; Rubber; Leakage current; neural network; polymeric insulator; salt-fog test;
Journal_Title :
Power Delivery, IEEE Transactions on
DOI :
10.1109/TPWRD.2005.858805
