摘要
本文针对模拟电路提出了1种新的基于紧致型小波神经网络的故障诊断方法。该方法首先利用小波变换和主成分分析对故障信号进行预处理,然后用处理后的故障特征数据对小波神经网络进行训练和测试。仿真实验表明,该方法比普通神经网络方法训练速度更快,诊断准确率更高。
This paper presents a new fault diagnosis method based on inlay model wavelet neural network for analog circuit. The method uses wavelet transform and principle component analysis to preprocess fault signal, afterward training and testing wavelet neural network with the preprocessed fault characteristic data. Experimentation indicates that the method has faster training speed and higher diagnosis nicety rate than general neural network method.
出处
《电子测量技术》
2006年第6期14-16,18,共4页
Electronic Measurement Technology
关键词
故障诊断
小波变换
主成分分析
小波神经网络
fault diagnosis
wavelet transform
principle component analysis, wavelet neural network