Classification of Single PD Sources of HV Transformer Insulation Faults using PRPD Pattern Features and ANN Approach

Abstract

Transformer is an expensive and vital component in electric power transmission and distribution system. Most of the failures of transformers occurs due to the failure of insulation. Hence electrical utilities are spending a large amount of money in the early prediction of insulation problems inside the transformers. In recent times, partial discharge (PD) detection and analysis is a well recognized insulation condition monitoring technique for power equipments. However, accurate classification of PD signals originating from different PD sources is always a vital and hot research issue. This paper attempts to use PRPD pattern features and artificial neural network approach, which produces accurate results on large data bases, to deal with partial discharge classification. In this work, corona discharges, internal discharges and surface discharges, which are the major sources of PD activities inside the transformer, were simulated in the laboratory using different electrode configurations and the corresponding PD signals were acquired using wide band detection system. Phase resolved PD pattern and time-frequency characteristics of PD pulses were analyzed and important statistical features were extracted. Artificial neural network model was trained and tested using the extracted statistical features of PRPD patterns of PD signals and reported results show that the proposed ANN based PD source classifier is efficient and useful for understanding single PD sources of transformers.