Neural network approach for fault diagnosis of transformers

Dissolved gas analysis (DGA) is one of the most useful techniques to detect the incipient faults of power transformer. This paper is a study of artificial neural networks (ANN) applications for the diagnosis of power transformer incipient fault. The fault diagnosis is based on dissolved gas-in-oil analysis (DGA). Using historical transformer failure data, a multi-layer perceptron (MLP) neural network is applied in this work. The proposed network can overcome the drawbacks of conventional methods. The proposed schemes are simulated and tested.