The use of some paradigms of neural networks in prediction of dielectric properties for high voltage liquid solid and gas insulations

Author

Mokhnache, L. ; Boubakeur, A.

Author_Institution

Dept. of Electr. Eng., Univ. of Batna, Algeria

fYear

2002

fDate

7-10 Apr 2002

Firstpage

306

Lastpage

309

Abstract

The aim of this paper is to reduce the ageing experiment time and predict thermal ageing stress for longest time intervals using some paradigms of artificial neural networks. We present also the prediction of the breakdown voltage in a point-barrier-plane air gap versus the gap length.

Keywords

ageing; air gaps; backpropagation; electric breakdown; insulation testing; organic insulating materials; power cable insulation; power engineering computing; power transformer insulation; radial basis function networks; transformer oil; PVC cables; RBF network; ageing time reduction; artificial neural networks; backpropagation; breakdown voltage; dielectric properties prediction; gap length; high voltage gas insulation; high voltage liquid insulation; high voltage solid insulation; longest time intervals; neural networks; point-barrier-plane air gap; thermal ageing stress prediction; transformer oil; Aging; Artificial neural networks; Cables; Dielectrics; Intelligent networks; Laboratories; Neural networks; Read only memory; Thermal stresses; Voltage;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical Insulation, 2002. Conference Record of the 2002 IEEE International Symposium on

Print_ISBN

0-7803-7337-5

Type

conf

DOI

10.1109/ELINSL.2002.995937

Filename

995937