Title :
Wavelet neural network method for fault diagnosis of push-pull circuits
Author :
Luo, Zhi-Yong ; Shi, Zhong-ke
Author_Institution :
Coll. of Autom., Northwestern Polytech. Univ., Xi´´an, China
Abstract :
A wavelet neural network method for fault diagnosis of push-pull circuits is presented. Firstly, output voltage signals under faulty conditions are obtained with simulation. Then wavelet coefficients of output voltage signals are gained by Daubechies wavelet decomposition, and faulty feature vectors are extracted from coefficients. After training the networks by faulty feature vectors, the wavelet neural networks model of the circuit fault diagnosis system is built. The simulation result shows the fault diagnosis method of the push-pull circuits with wavelet neural network is effective.
Keywords :
circuit simulation; fault diagnosis; feature extraction; learning (artificial intelligence); neural nets; wavelet transforms; Daubechies wavelet decomposition; circuit simulation; fault diagnosis; faulty feature vector extraction; neural net training; output voltage signal; push-pull circuit; wavelet neural network; wavelet transform; Circuit faults; Circuit simulation; Fault diagnosis; Neural networks; Power system modeling; Pulse transformers; Pulse width modulation; Space vector pulse width modulation; Voltage; Wavelet coefficients; Fault diagnosis; push-pull circuits; simulation; wavelet neural networks; wavelet transform;
Conference_Titel :
Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on
Conference_Location :
Guangzhou, China
Print_ISBN :
0-7803-9091-1
DOI :
10.1109/ICMLC.2005.1527517
