基于神经网络的模拟电路故障诊断

针对目前模拟电路故障诊断中存在的容差和非线性特性所带来的诊断难点,提出了一种基于LM算法的神经网络故障诊断方法;主要包括故障特征的选取以及神经网络的建立.其中网络隐含层节点数的选取采用黄金分割优选法.试验仿真表明,LM算法明显提高了网络训练速度,减少了训练时间,其效果优于标准BP算法,可有效提高故障诊断性能.

Fault Diagnosis in Analog Circuits Based on Neural Networks

The tolerance and nonlinearity in analog circuit make its fault diagnostic difficult. In order to solve this prob- lem, we present a method of neural network fault diagnosis is presented based on a Levenberg-Marquardt algorithm, which includes fault characteristic extracting, optimization design of network structure. Besides, an optimization algorithm based on the principle of golden section is adopted to design the number of hidden layer nodes in neural network. The simulation experiments shows that the Levenberg-Marquardt algorithm is superior to that of standard BP, which obviously quickens training speed and decreases training time, and the application effect is notable.