摘要： 针对模拟电路故障诊断难的问题，提出交叉熵方法加权子空间特征集成支持向量机的模拟电路故障诊断方法。对跳蛙滤波电路的故障诊断仿真实验表明，该方法获得训练集和测试集的故障诊断率分别为89%和88.6%，相比常用的BPNN、GENN、O-V-O SVM和基于随机子空间方法的支持向量机故障诊断方法，能获得更高的故障诊断率。
关键词:
模拟电路,
故障诊断,
随机子空间方法,
交叉熵方法,
支持向量机
Abstract: Aiming at the problem of analog circuit fault diagnosis, a novel approach based on random subspace method and Support Vector Machine(SVM) is presented. Simulation results of diagnosing the international benchmark circuits-leapfrog filter, compared with several existent fault diagnosis methods such as BPNN, GENN, O-V-O SVM, show that the proposed method has the highest classification accuracy.
Key words:
analog circuit,
fault diagnosis,
Random Subspace Method(RSM),
Cross Entropy Method(CEM),
Support Vector Machine(SVM)
中图分类号:
纪四维, 李熊达, 唐静远, 师奕兵. 模拟电路故障诊断的子空间集成方法[J]. 计算机工程, 2011, 37(17): 291-292,封三.
JI Si-Wei, LI Xiong-Da, TANG Jing-Yuan, SHI Yi-Bing. Subspace Ensemble Method for Analog Circuit Fault Diagnosis[J]. Computer Engineering, 2011, 37(17): 291-292,封三.