一种基于小波-神经网络的模拟电路故障诊断方法

小波分析具有数据压缩和特征提取的特性,神经网络具有非线性映射和学习推理的优点。结合两者的特点,提出了一种基于小波与神经网络的模拟电路故障诊断方法,该方法用小波变换对电路响应信号进行特征提取,从而简化神经网络的结构,降低计算的复杂度,加快了训练速度。对实例仿真表明,该法能有效地对模拟电路进行故障诊断。

An Analog Circuit Fault Diagnosis Method Based on Wavelet and Neural Network

Combining the extracting feature vectors and compressing data characteristics of wavelet transform with the nonlinear mapping and generalizing of neural network,a method of analog circuit fault diagnosis based on wavelet and neural network is presented.It abstracts the fault character information of circuit output signal by using wavelet transform effectively,thus,the neural network architecture can be simplified,the computation complexity can be reduced,and the training speed can be also improved.Finally,the simulation experiments show this method is effective for fault diagnosis of analog circuit.