基于小波神经网络的电路故障诊断方法  

Wavelet-neural network-based fault diagnosis approach for analog circuits

作　　者：谭杰[1] 谢胜曙[1] 尹新[1] 

机构地区：[1]湖南大学电气与信息工程学院,长沙410082

出　　处：《仪器仪表用户》2006年第6期102-103,共2页Instrumentation

摘　　要：本文根据小波神经网络故障诊断的基本思想,提出了一种基于“小波系数特征故障”的小波预处理神经网络模拟电路故障诊断方法。实验仿真结果表明,使用该方法提取故障特征加快了BP神经网络的训练速度,能迅速有效地进行故障检测和定位。A fault diagnosis method based on ＂coefficient feature fault＂ is presented in this article, which is according to the basic idea of wavelet and neural network approach for fault diagnosis of analog circuit .The proposed method uses wavelet decomPosition as the preprocessor Of BPNN .The result of simulation shows that circuit fault can be detected and located quickly by using this method and the training speed of BPNN is dramatically accelerated and effective.

关 键 词：故障诊断 神经网络 小波分析 

分 类 号：TM13[电气工程—电工理论与新技术]