基于RS-PSO-SVM集成的模拟电路软故障诊断  

Analog Circuit Soft Fault Diagnosis Based on RS-PSO-SVM Integration Classifier

作　　者：孙健 胡国兵 邓韦[2] 王成华[3] SUN Jian;HU Guobin;DENG Wei;WANG Chenghua(School of Electronic Information Engineering,JinlingInstitute of Technology,Nanjing 211169,P.R.China;College of Communication,Nanjing Vocational College of Information Technology,Nanjing 210023,P.R.China;College of Electronic and Information Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,P.R.China)

机构地区：[1]金陵科技学院电子信息工程学院,南京211169 [2]南京信息职业技术学院通信学院,南京210023 [3]南京航空航天大学电子信息工程学院,南京210016

出　　处：《微电子学》2020年第2期227-231,共5页Microelectronics

基　　金：国家自然科学基金资助项目(61701204);江苏省自然科学基金资助项目(BK20161104);金陵科技学院高层次人才科研启动基金资助项目(jit-b-201631)。

摘　　要：针对模拟电路软故障诊断准确度不高的问题,提出一种基于粗糙集(RS)-粒子群算法(PSO)-支持向量机(SVM)集成的模拟电路软故障诊断方法。首先利用粗糙集理论对采集的模拟电路软故障特征信息进行维数约简,然后利用粒子群算法对支持向量机的参数进行优化,以提高支持向量机分类器的诊断性能,最后进行故障诊断。对四运放双二次高通滤波器进行仿真,实验结果表明,基于RS-PSO-SVM集成的模拟电路软故障诊断方法是有效的。与其他常用方法相比,该诊断方法具有更好的故障诊断性能。An analog circuit soft fault diagnosis method based on rough set(RS)-particle swarm optimization(PSO)-support vector machine(SVM) integration was presented to solve the problem of low accuracy of soft fault diagnosis for analog circuit. Firstly, the rough set theory was used to reduce the dimension of analog circuit soft fault feature information. Then, in order to improve the diagnosis performance of support vector machine classifier, the particle swarm optimization algorithm was used to optimize the parameters of support vector machine. Finally, different faults were identified. Simulations results on four opamp biquad high-pass filter showed that the proposed method of analog circuit soft fault diagnosis based on RS-PSO-SVM integration was effective, and it had better fault diagnosis performance than other commonly used methods.

关 键 词：粗糙集 粒子群算法 支持向量机 模拟电路 故障诊断 

分 类 号：TN707[电子电信—电路与系统]