基于神经网络的模拟电路故障诊断研究  

Efficient Fault Diagnosis Method in Analog Circuits Based on Neural Network

作　　者：廖薇[1] 许春冬[2] 刘锦高[1] 

机构地区：[1]华东师范大学信息学院电子系,上海200241 [2]江西理工大学信息工程学院,江西赣州341000

出　　处：《微电子学与计算机》2010年第5期125-128,共4页Microelectronics & Computer

基　　金：上海市科技攻关重点项目(075115002)

摘　　要：针对模拟电路,提出一种基于神经网络的故障诊断方法.通过故障字典的建立,选择电路的最佳测试节点,电路故障响应进行预处理后得到故障特征向量,再输入到神经网络实现电路故障诊断.仿真结果表明:该方法有效地解决了模拟电路辨识难的问题,具有更好的故障分辨率,取得了满意的诊断效果.A method of fault diagnosis in analog circuits based on neural network is presented. Building the fault dictionary,the feature of fault response of analog circuits is abstracted and fed into neural network. Then the fault diagnosis in analog circuits is realized. Detailed simulation process and results propose that the difficult identification problem in analog circuits is resolved well,faults are classified well,and the diagnosis results are satisfied.

关 键 词：神经网络 模拟电路 故障诊断 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]