Classification of power quality disturbances using wavelet and artificial neural network

This paper presents a method of classification of power quality disturbances using Wavelet transforms combined with artificial neural network. Multi-resolution Wavelet analysis has been used as feature extractor, with different mothers Wavelet. Result comparison has been made in two levels: first, using different wavelet mothers, to determinate if the classification performance is better with a specific wavelet transform. The second level has been done using two differents Artificial Neural Network (ANN): backpropagation (BP) y Probabilistic Neural Network (PNN).