Abstract: This paper introduced fault diagnosis system for power transformer using an Artificial Neural Network (ANN). This system is to identify, localize and classify the faults. This system consists of various stages. In first stage, a preprocessing procedure for input data is performed. In second stage an ANN is designed to identify fault and to localize its side. In third stage, there are two sub diagnosis systems. Each system has one ANN designed to classify the fault. The performance of fault diagnosis system is evaluated using samples from local measurements (three-phase primary voltage and primary& secondary currents).The faults that are detected and cleared are single winding, double winding, and inrush currents.

Keywords: ANN, Power Transformer, Fault Protection.