Discrimination between Inrush Current and Internal Fault of Power Transformer based on MRA-ANN

The power transformer is an important component of the overall ingredients of the power system. In the protection of power transformer, discrimination between inrush current and internal fault current of transformer is an important problem. This paper is presented a new method based on Multi Resolution Analysis (MRA) and artificial Neural Networks (ANN) for digital differential protection. Some important characteristics of differential currents in the real power transformer operating conditions are extracted based on MRA. Also, the ANNs are proposed as the core classifier. This paper presents an effective and fast technique, for differentiating the magnetizing inrush and the internal fault of a power transformer by incorporating MRA and ANN. MRA-ANN structures are investigated in the worst case operational noise condition. The effectiveness of the proposed method is tested using numerous inrush and internal fault currents. The obtained results are employed to verify the suitability and the ability of the proposed method in discriminating inrush current from internal fault.