基于Fisher准则函数的相关向量机模拟电路故障诊断  

RVM analog circuit fault diagnosis based on Fisher criterion function

作　　者：杨颖涛[1] 王跃钢[1] 邓卫强[1] 

机构地区：[1]第二炮兵工程学院,西安710025

出　　处：《计算机应用研究》2011年第6期2085-2087,2112,共4页Application Research of Computers

基　　金：国家"973"计划资助项目(61355020301)

摘　　要：针对模拟电路故障与特征间存在的模糊组及交叠、分类效果不理想的情况,提出基于Fisher准则函数的最佳聚类数自适应估计方法和基于稀疏贝叶斯相关向量机(RVM)理论的模拟电路故障诊断模型,采用模糊核聚类选择最优可诊断故障集,然后在贝叶斯框架下对故障进行分类。该模型可以对分类函数的权重进行推断,辅助进行诊断决策,提高了RVM模拟电路故障分类的效率和准确度。仿真表明提出的诊断模型在精度提高的情况下,更具稀疏性和泛化性。In order to reducing fuzzy group and overlap of analog circuit between fault and feature,improving classify ability of analog circuit fault diagnosis,used new approach of fuzzy nuclear cluster to select best diagnosable fault component set based on Fisher criterion function,and proposed a fault diagnosis model for analog circuit based on relevant vector machine（RVM） from the sparse Bayesian theory.First,established auto-adapted estimating approach for best cluster number,then could infer the discriminant function under the Bayesian framework.Moreover,it could judge the degree of confidence of classification result,assist diagnosis decision-making.The result indicates that RVM need less RVs than SVs with comparative default accuracy,sparser and generalizing.

关 键 词：相关向量机 Fisher准则函数 模糊核聚类 稀疏贝叶斯 模拟电路 故障诊断 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]