关键词: 小波神经网路, LM算法, 模拟电路, 故障诊断, PSpice

Abstract: Fault diagnosis of analog circuit is accomplished based on LM algorithm combined with wavelet neural network.After multi-scale decomposition and normalization of impulse response signal,feature information is extracted and categorized as the neural network.The fault diagnosis method achieves efficient identification of analog circuits by combing PSpice and Matlab with significantly improved convergence and fault accuracy.Simulation results show that the network trained with sample set by this method offers better accuracy than those by traditional methods in fault diagnosis of analog circuits,and is applicable to the neural network.

Key words: wavelet neural network;Leven-Marquardt algorithm;analog circuit;fault diagnosis;PSpice