摘要
针对容差模拟电路故障诊断中软故障诊断样本较少和正确率低的问题,提出一种基于正弦余弦算法(Sine Cosine Algorithm,SCA)优化的容差模拟电路软故障诊断方法。对实验电路进行Monte Carlo分析后采集输出电压信号后采用小波变换提取小波熵组成故障特征集,采用主元分析法(Principal Component Analysis,PCA)对特征降维,利用基于SCA的支持向量机(Support Vector Machine,SVM)对故障集进行分类。通过对Sallen-Key带通滤波电路的分析,SCA-SVM分类算法具有较好的分类准确率与较快的诊断速度,优于网格搜索(GridSearch)、遗传算法(GA)和粒子群算法(PSO)。最后,在四运放双二次高通滤波器电路上进行测试。结果表明,SCA-SVM在容差模拟电路软故障诊断中具有较强的适应能力。
With regard to the lack of the sample and low accuracy in analog circuit fault diagnosis, a method based on the sine cosine algorithm is proposed for soft fault diagnosis in analog circuit with tolerance. Firstly, Monte Carlo analysis was carried out on the experimental circuit and then the output voltage signal collected as dataset. Then the wavelet entropy is calculated from dataset transformed by the wavelet transform, which form fault feature dataset, the principal component analysis（PCA） is used for feature dimension reduction. Finally, the support vector machine（SVM） optimized by SCA is employed to classify the fault dataset. Experiment on the Sallen-Key band-pass filter circuit analysis shows that the SCASVM classifier has higher classification accuracy and faster iteration speed than GridSearch, genetic algorithm（GA） and particle swarm optimization（PSO）. Testing experiment on the four-opamp biquad highpass filter circuit indicates excellent adaptive capacity in analog circuit fault diagnosis.
作者
朱静
何玉珠
崔唯佳
ZHU Jing;HE Yu-zhu;CUI Wei-jia(Chengdu Aeronautic Polytechnic,Chengdu 610100;School of Instrumentation Science and Opto-electronics Engineering,Beijing University of Aeronautics and Astronautics,Beijing 100191)
出处
《导航与控制》
2018年第4期33-40,共8页
Navigation and Control
基金
四川省教育厅科研项目(编号:17ZB0038)
关键词
正弦余弦算法
支持向量机
模拟电路
故障诊断
sine cosine algorithm（SCA）
support vector machine（SVM）
analog circuit
fault diagnosis
作者简介
姓名：朱静性别：男学历：硕士研究生职称：助教研究方向：电子系统PHM、机器学习
