A neural network based method for the diagnosis of ageing insulators

Abstract

This work attempts to apply an artificial neural network in order to diagnose ageing transmission line insulators. The insulator leakage current harmonic components are used as the input variables of the artificial neural network. The data used to train the network and test its performance is derived from experimental measurements carried out in artificial climatic chamber. The experimental result and neural network simulation results are presented accordingly. This novel method of ANN application can be viable in online diagnosis of insulators in service and lifespan estimation yielding efficient and effective predictive maintenance practices for power utilities in a cheap and less time-consuming manner.