Numerical differential protection of power transformer using ANN as a pattern classifier

This paper presents the use of ANN as a pattern classifier for differential protection of power transformer, which makes the discrimination among normal, magnetizing inrush, over-excitation, external fault and internal fault currents. This scheme has been realized through two ANN architectures, which are designed and trained using feed forward back propagation algorithm with experimental data and finally one architecture is selected. The results amply demonstrate the capabilities of ANN in terms of accuracy and speed for identification of different events of power transformer. The trained and tested results indicate that it is fast and reliable.