基于小波神经网络的模拟电路故障诊断方法研究  

Method of Analog Circuit Fault Diagnosis based on wavelet neural network

作　　者：周晶晶[1] 吴文全[1] 许炎义[1] 孙金明[1] 

机构地区：[1]海军工程大学电子工程学院,湖北武汉430033

出　　处：《现代电子技术》2015年第6期36-38,共3页Modern Electronics Technique

摘　　要：小波变换是一种时频分析方法,具有多分辨率特性,被誉为数学显微镜,而BP神经网络具有较好的泛化能力,很适合于判断电路状态属于哪种故障类型的分类问题。本文将二者结合起来,采用基于小波神经网络的模拟电路故障诊断方法。应用小波变换对模拟电路幅频响应的采样信号进行故障特征提取,然后利用BP神经网络对各种状态下的特征向量进行分类决策,实现模拟电路的故障诊断。通过对电路进行仿真,证明该方法能够实现故障检测及定位,具有准确率高的特点。Wavelet transform is a time？frequency analysis method,which has multi？resolution feature,is honoured as mathematical microscope,and is suitable for judging what type of fault the circuit status belongs to. In this paper,the analog cir？cuit fault diagnosis method based on wavelet neural network is used. Wavelet transform is adopted to extract the fault features of the sampling signal from amplitude？frequency response of the analog circuit. BP neural network is utilized to classify the feature vectors under various states and realize fault diagnosis of analog circuits. Simulation results of the circuit show that this scheme is feasible and has many powerful virtues,such as accurate fault detection and positioning.

关 键 词：小波变换 模拟电路故障诊断 神经网络 故障特征提取 

分 类 号：TN710-34[电子电信—电路与系统]