J. Phys. IV France 124 (2005) 147-151
DOI: 10.1051/jp4:2005124023

Neural networks in prediction of thermal ageing effect on oil/paper insulation electrical properties

L. Mokhnache¹, P. Verma², A. Boubakeur³ and R. Kattan<sup>4

1</sup>  University of Batna, Faculty of Engineering, Dept. of Electrical Engineering, L.S.P-I.E, Batna, Algeria
²  Thapar Institute of Engineering & Technology, Patiala 147 004, India
³  École Nationale Polytechnique, High voltage Lab., Avenue Hacène Badi, El-Harrach, Algers, Algeria
⁴  Université Libanaise, Faculty of Sciences, Physics Department, Beyrouth, Lebanon

Abstract
This paper presents in a first part an experimental study on the effect of thermal ageing on Oil/Paper Insulation Electrical Properties. In the second part, artificial neural networks (RBFG) have been applied to predict the electrical properties for longest ageing periods.

© EDP Sciences 2005