摘要
在阐述了小波变换和BP(反向传播)神经网络概念的基础上,根据小波神经网络故障诊断的基本思想,提出了一种基于“能量故障”的小波预处理神经网络故障诊断方法。实验仿真结果表明,使用该方法提取故障特征加快了神经网络的训练速度,能迅速地进行故障的检测和定位。
After introducing the conception of wavelet transfer and the architecture of BPNN, a fault diagnosis method based on “energy - fault” is presented, which is according to the basic idea of fault diagnosis of wavelet and neural network. 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.
出处
《电子工程师》
2005年第8期67-70,共4页
Electronic Engineer
关键词
故障诊断
神经网络
小波分析
故障特征
fault diagnosis, neural networks, wavelet analysis, fault feature
