模糊聚类与SVM诊断模拟电路单软故障的方法  

Fuzzy Clustering and SVM Method for Diagnosing Analog Circuits Single Soft Fault

作　　者：孙永奎[1] 陈光 李辉[2] 

机构地区：[1]电子科技大学自动化工程学院,成都610054 [2]电子科技大学空天科学技术研究院,成都610054

出　　处：《计算机辅助设计与图形学学报》2008年第5期612-617,共6页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(60372001,90407007)

摘　　要：针对低可测性模拟电路中存在的模糊组问题,提出一种模拟电路单个软故障诊断的方法.该方法对被测电路的故障进行模糊聚类,根据聚类的有效性指标自适应确定聚类数,并利用聚类的信息来确定可测元件集,引入支持向量机对故障进行分类识别.支持向量机结构简单、泛化能力强.最后,以模拟和混合信号测试标准电路证实了文中方法的有效性.A method for diagnosing single soft fault in analog circuits with low testability is presented in this paper. The faults of circuit under test are analyzed by fuzzy clustering algorithm and the fault classes are adaptively obtained by using the fuzzy clusters＂ validity indices. The testable component set is determined by the cluster results. Support vector machine （SVM） is introduced to identify the analog circuit faults. SVM has advantages of simple structure and strong generalization ability. Experimental results on analog and mixed-signal benchmark circuits demonstrated the efficiency of the proposed method for diagnosing analog circuits＇ single soft fault which based on fuzzy clustering analysis and SVM.

关 键 词：模拟电路 故障诊断 模糊聚类 支持向量机 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TM930[自动化与计算机技术—控制科学与工程]