Different defects diagnosis of an elecrical power transformer bushings

Abstract

The transformer is the most important electrical power system equipment used to transmit and distribute the electricity. The bushings are among the vital accessories components in the transformer because of the different defects which can be produced in this part. The aim of the present work is to diagnose the different defects in an electrical transformer bushings based on the dissolved gas analysis method (DGA). The DGA is an effective technique to diagnosis and guarantee an early detection of incipient faults in transformer bushings for reducing unplanned outages. However, this method may not successfully identify certain defects. Multi Layer Perceptron (MLP) neural network is applied as simulation tool to resolve this problem. The results obtained by MLP are compared with those obtained by DGA and the literature, which allowed us to conclude that MLP can diagnosis and classify different defects of bushings in good way. Therefore, the MLP neural network can be used very large to predict the defects of transformer bushings.