WAVELET PACKETS ANALYSIS AND ARTIFICIAL INTELLIGENCE BASED ADAPTIVE FAULT DIAGNOSIS

Former fault diagnosis algorithms for the transmission systems usually employ FFT and deterministic thresholds. These bring simplicity along with lots of manual works and inaccuracy to the applications. This paper proposes a new adaptive fault diagnosis scheme, which hardly need any interference from users. It utilizes the Wavelet Packets Transformation Analysis (WPTA) as a preliminary feature extractor and a Neural Network (NN) as the pattern classifier. Extensive simulation studies show that the wavelet packets transform provides an effective signal representation for classification. The combination of the WPTA and NN achieves outstanding performance and the ability to adapt to various network settings. Without any structure modification, the scheme can be applied to different networks. Keyword: system protection, wavelet packets, neural networks,

[1]  Christopher John Long,et al.  Wavelet based feature extraction for phoneme recognition , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[2]  James L. McClelland,et al.  James L. McClelland, David Rumelhart and the PDP Research Group, Parallel distributed processing: explorations in the microstructure of cognition . Vol. 1. Foundations . Vol. 2. Psychological and biological models . Cambridge MA: M.I.T. Press, 1987. , 1989, Journal of Child Language.

[3]  Ruxu Du,et al.  FEATURE EXTRACTION AND ASSESSMENT USING WAVELET PACKETS FOR MONITORING OF MACHINING PROCESSES , 1996 .

[4]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[5]  Alan S. Willsky,et al.  A Wavelet Packet Approach to Transient Signal Classification , 1995 .

[6]  Kevin Gilholm,et al.  Signal and image feature extraction from local maxima of generalised correlation , 1998, Pattern Recognit..

[7]  André Quinquis,et al.  Magnetic Noise Substraction With Wavelet Packets , 1996, Fourth International Symposium on Signal Processing and Its Applications.

[8]  David Chan Tat Wai,et al.  A novel technique for high impedance fault identification , 1998 .

[9]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[10]  R.K. Aggarwal,et al.  A New Approach to Phase Selection Using Fault Generated High Frequency Noise and Neural Networks , 1997, IEEE Power Engineering Review.

[11]  Amara Lynn Graps,et al.  An introduction to wavelets , 1995 .

[12]  Ronald R. Coifman,et al.  Signal processing and compression with wavelet packets , 1994 .

[13]  D. L. Waikar,et al.  Symmetrical component based improved fault impedance estimation method for digital distance protection Part I. Design aspects , 1993 .

[14]  Arun G. Phadke,et al.  Power System Relaying , 1992 .

[15]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[16]  Bernhard Bachmann,et al.  Application of artificial neural networks for series compensated line protection , 1996, Proceedings of International Conference on Intelligent System Application to Power Systems.

[17]  Truong Q. Nguyen,et al.  Adaptive wavelet packet based image coding with optimal entropy-constrained lattice vector quantizer (ECLVQ) , 1998, IEEE Trans. Signal Process..

[18]  Adly A. Girgis,et al.  Application of adaptive Kalman filtering in fault classification, distance protection, and fault location using microprocessors , 1988 .