Power transformer differential protection scheme based on wavelet transform and artificial neural network algorithms

This paper proposes a differential protection scheme for power transformers using wavelet transform and neural network algorithms. It utilizes the wavelet transformation (WT) analysis as a preliminary feature extractor and an artificial neural network (ANN) as the pattern classifier. Extensive simulation studies show that the wavelet transform provides an effective signal representation for classification of different transient cases. The combination of WT and ANN achieves outstanding performance and the ability to discriminate internal faults fast and accurately. Details of the proposed relay design are given in the paper. Some performance studies results are also given.