Improving training of radial basis function network for classification of power quality disturbances

Author

Hoang, T.A. ; Nguyen, D.T.

Author_Institution

Sch. of Eng., Tasmania Univ., Hobart, Tas., Australia

Volume

38

Issue

17

fYear

2002

fDate

8/15/2002 12:00:00 AM

Firstpage

976

Lastpage

977

Abstract

Features extracted from non-stationary and transitory power quality disturbances using wavelet transform modulus maxima can serve as powerful discriminating features for wavelet-based classification of these disturbances. Using these features, a comprehensive ´knowledge-based´ algorithm is proposed for the training of the radial basis function 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; feature extraction; learning (artificial intelligence); pattern classification; power engineering computing; power supply quality; radial basis function networks; wavelet transforms; RBF network classifier; cluster centres; convergence; feature extraction; knowledge-based algorithm; nonstationary disturbances; optimal feature weight vector; power quality disturbances classification; radial basis function network; scaling widths; training; transitory power quality disturbances; wavelet transform modulus maxima; wavelet-based classification;

fLanguage

English

Journal_Title

Electronics Letters

Publisher

iet

ISSN

0013-5194

Type

jour

DOI

10.1049/el:20020658

Filename

1031794