Title :
A comprehensive training for wavelet-based RBF classifier for power quality disturbances
Author :
Hoang, T.A. ; Nguyen, D.T.
Author_Institution :
Tasmania Univ., Hobart, Tas., Australia
Abstract :
In this paper we demonstrate that the dominant frequencies and Lipschitz exponents in nonstationary and transitory power quality disturbances efficiently extracted from their wavelet transform modulus maxima (WTMM) in the time-scale domain can serve as powerful discriminating features for wavelet-based classification of these disturbances. We also propose a comprehensive "knowledge-based" algorithm for the training of the radial basis function (RBF) network classifier so that at its convergence, the network gives both the optimal feature weight vector as well as the cluster centres and scaling widths.
Keywords :
convergence of numerical methods; learning (artificial intelligence); pattern classification; power supply quality; power system analysis computing; power system faults; radial basis function networks; time-domain analysis; wavelet transforms; Lipschitz exponents; RBF network classifier; WTMM; cluster centres; convergence; discriminating features; dominant frequencies; knowledge-based algorithm; nonstationary power quality disturbances; optimal feature weight vector; power quality disturbances; radial basis function network classifier; scaling widths; time-scale domain; training; transitory power quality disturbances; wavelet transform modulus maxima; wavelet-based RBF classifier; wavelet-based classification; Clustering algorithms; Frequency; Monitoring; Power quality; Power supplies; Power system harmonics; Power system transients; Voltage; Wavelet domain; Wavelet transforms;
Conference_Titel :
TENCON '02. Proceedings. 2002 IEEE Region 10 Conference on Computers, Communications, Control and Power Engineering
Print_ISBN :
0-7803-7490-8
DOI :
10.1109/TENCON.2002.1182713