基于小波包分析与RBF神经网络的模拟电路故障诊断

Fault Diagnosis of Analog Circuit Based on Wavelet Packet Analysis and RBF Neural Network

针对常用的BP神经网络须已知结构,且学习算法训练速度慢的缺点,提出一种基于小波包分析与径向基神经网络(RBFNN)的模拟电路故障诊断方法。该方法首先利用小波包分解,归一化作为预处理提取模拟电路的故障特征向量,再将故障特征向量输入到RBF神经网络进行故障诊断。仿真结果表明本方法能够对模拟电路的故障进行有效诊断和定位。

As tho Bpneura not work has do know the strure and learning algrithm, algoriam, besides it trains slonly A method for fault diagnosis of analog circuits based on the combination of wavelet packet analysis and RBF neural network is presented. The feature information was extracted first by using wavelet packet analysis method, and then was applied to the proposed neural network for further analysis and classification of fault patterns. The simulation result shows that the proposed method is effective in fault diagnosis of analog circuits.