By Topic

The Use of Experimental and Artificial Neural Network Technique to Estimate Age against Surface Leakage Current for Non-ceramic Insulators

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Elkhodary, S.M. ; Dept. of Elec. P/M, Ain Shams Univ. ; Nasrat, L.S.

Solid insulators breakdown mechanism is always associated with surface leakage current. Surface leakage current causes surface tracking. Surface tracking in non-ceramic insulators is an unwanted phenomenon, which cannot be accurately predicted. This paper introduces an experimental and analytical technique to predict the insulator life time, and presents an experimental measurements of the surface leakage current against time of nonceramic insulators on naturally aged insulators and artificially contaminated material. A comparison of surface leakage current for fourteen different type of non-ceramic materials under the same conditions is also introduced in this paper (the mentioned nonceramic materials are mainly silicon rubber (SR) and poly propylene (PP), with different filler percentage). The study of the leakage current dependence on the insulators contamination level is also presented in this paper. Different prototype of artificial neural networks-based system that can estimate the insulator age under different contamination level at the surface of polymer insulators by employing the experimentally measured leakage current was constructed in this paper. The proposed prototype is trained for different filler level for different insulator type in the neural network. The proposed technique in this paper predicts the best non-ceramic insulator with the exact filler percentage that withstands higher voltage with longer life time under contaminated weather and polluted condition. The proposed technique is considered to be helpful tool in the area of quality control

Published in:

Power Engineering, 2006 Large Engineering Systems Conference on

Date of Conference:

26-28 July 2006