基于小波因子分析的PSO-ELM模拟电路故障诊断  

Analog circuit fault diagnosis based on wavelet analysis optimized by factor analysis and PSO-ELM

作　　者：夏爽 颜学龙[1] Xia Shuang;Yan Xuelong(School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China)

机构地区：[1]桂林电子科技大学电子工程与自动化学院

出　　处：《国外电子测量技术》2018年第9期46-50,共5页Foreign Electronic Measurement Technology

基　　金：广西自动检测技术与仪器重点实验室基金项目(YQ17101)资助

摘　　要：为了解决模拟电路故障诊断中故障元件定位难,诊断率低的问题,提出采用因子分析优化的小波分析和粒子群优化极限学习机的模拟电路故障诊断的方法。该方法首先对采集到的模拟故障数据进行小波分析故障特征提取,然后利用因子分析技术构建采样数据的相关矩阵求出因子载荷和因子得分,按照累计贡献率自动提取出少数因子组成特征向量,最后将提取的故障特征输入粒子群优化的极限学习机进行故障诊断。仿真结果表明,该方法具有良好的区分能力,提高了训练速度和诊断效率。In order to solve the problem of fault location and fault diagnosis in analog circuit fault diagnosis,an approach utilizing wavelet analysis optimized by factor analysis and extreme learning machine（ELM）is proposed.Firstly,the wavelet analysis of fault features was extracted from the sampled analog fault data.Then,constructing a correlation matrix of sample data computed factor loadings and factor score by using factor analysis and extract a few factors to compose the eigenvector according to the cumulative contribution rate.Finally,the obtained fault feature was imported into the extreme learning machine optimized by particle swarm optimization for troubleshooting.The simulation results show that the proposed method can extract the fault signature effectively and increasing the training speed and diagnostic efficiency.

关 键 词：模拟电路 极限学习机 小波分析 因子分析 

分 类 号：TN707[电子电信—电路与系统]