摘要
提出一种基于小波变换多分辨率特征提取的模拟电路故障诊断的方法。该方法先对采样后的故障信号进行小波分解,提取各频段系数作为特征向量输入到神经网络进行训练。通过带通滤波器电路诊断的实例,阐述该方法的具体实现,验证该方法可以有效地简化神经网络结构和减少它的训练时间,快速高效地进行模拟电路故障的诊断和定位。
This paper researches the method based on the wavelet multi-resolution feature extraction for analog circuit fault diag- nosis. The features of sampling signal are extracted from wavelet decomposition as a vector to BP neural network for training. Ac- cording to bandpass filter circuit of diagnosis example, this paper discusses the specific implementation of this method. It can ef- fectively simplify neural network structure and reduce its training time, quickly and efficiently carry out analog circuit fault diag- nosis and positioning.
出处
《计算机与现代化》
2012年第9期181-183,189,共4页
Computer and Modernization
关键词
小波分析
神经网络
模拟电路
故障诊断
wavelet analysis
neural network
analogue circuits
fault diagnosis
