Neural network–based methodology to study effects of oil properties on induction period evaluated from response of oil-paper insulation employing mineral oil, ester, and mixture

Abstract

Induction period evaluated from time domain dielectric response of oil-paper insulation (OPI) contains information related to heat dissipating property of oil. In the present paper, effect of aging sensitive oil properties on the value of induction period is investigated. Three types of dielectric liquids (pure mineral oil, synthetic ester, mixture of synthetic ester, and mineral oil) are considered for the present work. A neural network (NN) is used for modelling the non-linear relationship between induction period and various oil properties. The trained network is subsequently used to study the influence of various oil properties on induction period.