Share Email Print
cover

Proceedings Paper

Implementation and performance results of wavelet network for analysis of fault signal in power system
Author(s): Weili Huang; Wei Du
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A new method is proposed to detect fault signal in power system using wavelet transform and neural network. The wavelet transform can decompose the original signal into several other signals with different levels of resolution. From these decomposed signals, the original time-domain signal can be recovered without losing any information. In order to increase the signal-noise-ratio, statistic rule is used to determine the wavelet decomposition level and threshold. Considering the inter relationship of wavelet decomposition coefficients, the signal features obtained from wavelet transform are presented for fault pattern classification. According to threshold value of each type of fault signal in each frequency band, the correlation between the type of signal and the signal features can be figured to fault pattern classification. As to this model, the advantages of morphological filter and wavelet transform are used to extract the fault feature meanwhile restraining various noises. The simulation results demonstrate that the proposed approach is verified to be effective.

Paper Details

Date Published: 9 October 2008
PDF: 4 pages
Proc. SPIE 7128, Seventh International Symposium on Instrumentation and Control Technology: Measurement Theory and Systems and Aeronautical Equipment, 712802 (9 October 2008); doi: 10.1117/12.806322
Show Author Affiliations
Weili Huang, Hebei Univ. of Engineering (China)
Wei Du, Hebei Univ. of Engineering (China)


Published in SPIE Proceedings Vol. 7128:
Seventh International Symposium on Instrumentation and Control Technology: Measurement Theory and Systems and Aeronautical Equipment

© SPIE. Terms of Use
Back to Top