摘要
利用小波变换与神经网络相结合的(WNT)方法,将小波作为消噪工具,对信号进行消噪和小波多尺度分解,提取特征信息。并从函数型和权值型小波神经网络中寻找最优故障辨识器,提出了模拟电路故障诊断的系统方法。本文详述了其诊断原理及诊断步骤,并给出了诊断实例。
A systematic method of fault diagnosis for analogue circuits based on the combination of Neural network with Wavelet Transform (WNT) is presented in the paper. Using the wavelet decomposition as a de-noise tool, the feature information is extracted by wavelet de-noise and its multi-resolution. The best fault classifier is obtained by comparing the performance of functional and weighted WNT. Diagnosis principles and steps are described. Finally, the reliability of the methods presented is shown by practical examples.
出处
《电子与信息学报》
EI
CSCD
北大核心
2006年第9期1748-1751,共4页
Journal of Electronics & Information Technology
基金
湖南省科技计划(03GKY3036)资助课题
关键词
故障诊断
模拟电路
神经网络
小波变换
Fault diagnosis, Analogue circuits, Neural networks, Wavelet Transform