基于模拟电路I_(DDT)的小波神经网络故障诊断方法  

A Method of Wavelet Neural Network for Fault Diagnosis Based on Analog Circuit IDDT

作　　者：刘美华[1] 李建明[1] 周建宇[1] 

机构地区：[1]湖南工程学院工程训练中心,湘潭411101

出　　处：《湖南工程学院学报（自然科学版）》2010年第4期14-16,共3页Journal of Hunan Institute of Engineering(Natural Science Edition)

摘　　要：动态电源电流(IDDT)对模拟电路故障诊断非常有效。通过分析被测电路的动态电源IDDT及其输出响应来识别电路的故障元件;用小波对被测信号进行多尺度分解,提取小波系数能量,经归一化后,作为特征向量输入到神经网络而实现故障诊断.实验仿真结果表明:该方法能正确实现故障定位且准确率高.Dynamic supply current test is very useful for fault diagnosis in analog circuits.Faulty components are identified by analyzing IDDT and impulse response of circuit under test.Wavelet analysis can be used to extract energy as feature information.After normalization,the features are applied to the proposed neural network and the fault pattern are classified.Simulation results show that the proposed method can locate fault with high accuracy.

关 键 词：模拟电路 小波分析 神经网络 故障诊断 

分 类 号：TP206.1[自动化与计算机技术—检测技术与自动化装置]