Wavelet-based classification of power quality disturbances using radial basis function networks

摘要

Classification of non-stationary and transitory power quality disturbances is a very challenging task. In this paper we demonstrate that wavelet transform modulus maxima (WTMM) can serve as powerful discriminating features of these transient disturbances. We also demonstrate that for these types of signals where training data is reasonably well clustered, a radial basis function (RBF) network is a more suitable classifier than a backpropagation neural network in terms of training speed and accuracy.