基于加权模糊支持向量描述的旋转机械故障分类  

Fault Classifier of Rotating Machinery Based on Weighted Fuzzy Support Vector Data Description

作　　者：张永[1] 张凤梅[1] 谢福鼎[1] 迟忠先[2] 

机构地区：[1]辽宁师范大学计算机系,大连116029 [2]大连理工大学计算机科学与工程系,大连116024

出　　处：《计算机科学》2009年第7期182-184,229,共4页Computer Science

基　　金：国家自然科学基金重大研究计划(No.90718030);辽宁省科技厅博士启动基金(No.20081079);辽宁省教育厅科学技术研究项目(No.2008347)资助

摘　　要：基于支持向量数据描述良好的分类性能,针对旋转机械故障诊断中故障样本获取的特点,提出了基于正负类样本的加权模糊支持向量数据描述多类分类器,不仅考虑了正类样本,而且也充分考虑了负类样本对分类结果的影响。利用模拟故障样本对系统进行了实验,结果表明提出的方法在系统中具有良好的分类能力。Based on the favorable classification performance of support vector data description（SVDD）, aiming at the problem of fault samples＇ acquisition in rotating machinery fault diagnosis, this paper proposed a fuzzy support vector data description classifier based on positive and negative samples,which can be used to deal with the outlier sensitivity problem in traditional multi-class classification problems. This method considers the effect of negative samples to classification results, as well as the positive samples in the traditional SVDD algorithm. Experimental results show that the proposed method can reduce the effect of outliers and yield higher classification rate than other existing methods.

关 键 词：支持向量数据描述 加权 分类器 支持向量机 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]