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

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.