T.A. Hoang and D.T. Nguyen (Australia)
Wavelets, Radial Basis Function Networks, Pattern Classification, Power Quality Disturbances
Wavelet-based classification of non-stationary and transitory power quality disturbances has recently attracted a great deal of interest from researchers. In this paper we demonstrate that the dominant frequencies and Lipschitz exponents in a transitory signal, efficiently extracted from the wavelet transform modulus maxima (WTMM) in the time-scale domain, can serve as powerful discriminating features of these transient disturbances. We also demonstrate how a radial basis function (RBF) network can be trained to outperform a backpropagation neural network in classifying these disturbances in terms of training speed and accuracy.
Important Links:
Go Back
