A New Approach for Transformer Incipient Fault Diagnosis Based on Dissolved Gas Analysis (DGA)

Transformer incipient fault diagnostic method based on dissolved gas analysis (DGA) using Artificial Neural Networks (ANN) and Neural-Imperialistic Competitive Algorithm (Nero-ICA) hybrid approach is simulated in this paper and the results has been compared with IEC standard. Firstly, dissolved gas analysis method and IEC DGA standard has been presented. In the second step, application of ANN and Nero-ICA for DGA interpretation where 30 data sample tests of different transformers have been selected very carefully in order to extract known as well as unknown diagnosis correlations implicitly and these samples are used for ANN and Nero-ICA test. Finally, the results obtained from Artificial Neural Networks and Nero-ICA is compared with the actual results. Simulation results show that Nero-ICA is more accurate and effective than ANN with simple structure, if training data increased more and more.