基于小波分解和BP网络模拟电路故障诊断研究  

Research on Analogous Circuit Fault Diagnosis Based on Wavelet Decomposition and BP NN

作　　者：徐昕[1] 傅煊[1] 

机构地区：[1]中国工程物理研究院电子工程研究所,四川绵阳621900

出　　处：《现代电子技术》2011年第19期171-175,共5页Modern Electronics Technique

基　　金：中国工程物理研究院科学技术发展基金(2009B0403044)

摘　　要：为了高效、准确地对模拟电路故障进行诊断,采用了一种基于小波多层分解和BP神经网络相结合的模拟电路故障诊断方法。该法利用了多层小波分解优异的时频特性来提取故障特征参数,结合了BP网络强大的非线性分类能力和快速的收敛特性。将该方法应用到模拟带阻滤波器单一软故障诊断中,仿真结果表明该方法是有效的,而且具有比传统BP网络方法的学习收敛速度快得多,诊断正确率高的特点。A analogous circuit fault diagnosis method based on wavelet decomposition and BP NN is proposed for diagnose the fault of analog circuit efficiently and accurately.The novel method makes full use of advantages of time-frequency localization of wavelet transform and self-learning of artificial neural network.An application on fault diagnosis of an analogous band-stop filter illustrates that the new method is feasible and effective.The simulation results show that the BP wavelet neural network has fast convergence and high diagnostic accuracy compared to conventional BP neural network.

关 键 词：小波分解 BP网络 软故障 特征提取 带阻滤波器 

分 类 号：TN711-34[电子电信—电路与系统]