非线性电路的神经网络故障诊断方法

Efficient fault diagnosis method in nonlinear circuits based on neural network

针对非线性动态电子电路,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,对电路故障响应进行预处理后得到的故障特征作为神经网络的输入,然后利用神经网络对各种状态下的特征向量进行分类决策,对故障类别进行辨识,并对电路进行了可测性分析,从而实现非线性电路的故障诊断。详细的仿真过程及结果表明,该方法有效地解决了非线性电路辨识难的问题,能较好地对故障模式进行分类,取得了满意的诊断效果。

A method of fault diagnosis in nonlinear dynamic circuits based on neural network is proposed.Building the fault dictionary,the feature of fault response of nonlinear circuits is abstracted and fed into neural network.The neural network is used to classify the feature vector in different condition and execute the fault identification.Testability analysis in circuit is executed. Then the fault diagnosis in nonlinear circuits is realized.Detailed simulation process and results propose that the difficult identification problem in nonlinear circuits is resolved well,fault models is classified well,and superior diagnosis efficiency is acquired.