基于Wiener核和BP神经网络的非线性模拟电路故障诊断  

Fault diagnosis in nonlinear analog circuit based on Wiener kernel and BP neural network

作　　者：林海军[1] 张礼勇[1] 任殿义 康辉[1] 顾耕[1] 

机构地区：[1]哈尔滨理工大学,哈尔滨150040 [2]哈尔滨电工仪表研究所,哈尔滨150081

出　　处：《仪器仪表学报》2009年第9期1946-1949,共4页Chinese Journal of Scientific Instrument

基　　金：黑龙江省自然基金项目(15008002-08045/F200825);哈尔滨市科技攻关项目(GJ2007GG009024)资助

摘　　要：研究提出基于非线性电路的Wiener核和BP神经网络的故障诊断方法。在输入为高斯白噪声的情况下,对输入、输出信号进行采样,通过计算各阶相关函数的方法得到正常及各种故障状态下非线性电路的Wiener核。把该核作为状态特征并进行适当的预处理,与对应的状态一起组成BP神经网络的输入和输出样本来对神经网络进行训练,从而实现对模拟非线性电路的故障诊断。文中给出了Wiener核的数字计算方法和诊断神经网络的建立方案,并通过诊断实例加以验证。A BP neural network diagnosis method based on Wiener kernel of nonlinear circuit is presented. In Gaussian white noise input case, the input and output signals are sampled, the Wiener kernel of the nonlinear circuit in normal state and a variety of fault states can be obtained by calculating each order correlation function. The kernel is taken as a state feature and extracted and preprocessed, which is combined with the corresponding states and used as the input/output samples of the BP neural network to train the neural network and realize fault diagnosis of the nonlinear analog circuit. The calculation method of Wiener kernel and the establishment scheme of the neural network diagnostic program are given, and a diagnosis example is also given to verify this method.

关 键 词：Wiener核 神经网络 非线性电路 故障诊断 相关函数 

分 类 号：TN707[电子电信—电路与系统]