基于神经网络的大规模模拟电路故障检测系统  

Large-scale Analog Circuit Fault Diagnosis Based on Neural Network

作　　者：吴欣[1] 张博[1] 陈涛[1] 

机构地区：[1]中国科学院长春光学精密机械与物理研究所,吉林长春130022

出　　处：《计算机测量与控制》2004年第11期1049-1051,共3页Computer Measurement &Control

摘　　要：设计了一个基于小波和神经网络的信号处理系统,该系统主要针对大规模模拟电路故障检测。针对传统诊断技术的局限性,讨论了利用神经网络方法分级诊断大规模模拟电路软故障的方案,通过小波变换提取故障特征,并利用神经网络的非线性映射特性逼近故障诊断模型。诊断结果表明基于人工神经网络的电路故障诊断方法是行之有效的。此方法具有广阔的应用前景,为大规模模拟电路故障诊断提供了新的理论依据和检测方法,并有希望研制成一套高效的检测设备。A design of a signal processing system based on neural network is proposed in the paper,this system is used to large-scale analog circuit fault diagnosis. Direct against the limitation of diagnosis technology in traditional, the scheme of large-scale simulation circuit soft trouble diagnosis is discussed by using neural network. By using wavelet transform to extract the fault performance, it utilizes neural non-linearity of network shone characteristic to approach trouble diagnosis models. Diagnosis result shows that the method of circuit fault diagnosis on basis of artificial neural network is effectual. This method is so promising and widely applicable that it provides a new theoretic proof and detecting approach. It may be executed to a high-efficient facility.

关 键 词：人工神经网络 大规模模拟电路 非线性映射 故障检测系统 明基 小波变换 逼近 信号处理系统 软故障 故障特征 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TN47[自动化与计算机技术—控制科学与工程]