| 基于粗糙集的支持向量机故障诊断 |
| |
| 引用本文： | 张建明,曾建武,谢磊,王树青.基于粗糙集的支持向量机故障诊断[J].清华大学学报(自然科学版),2007,47(Z2):1774-1777. |
| |
| 作者姓名： | 张建明 曾建武 谢磊 王树青 |
| |
| 作者单位： | 浙江大学,先进控制研究所,工业控制技术国家重点实验室,杭州,310027 |
| |
| 摘 要： | 该文结合粗糙集属性约简及支持向量机分类机理,提出了一种新的故障诊断方法。首先利用粗糙集对过程特征变量进行约简,去除冗余的过程信息,并降低过程数据的维数,获得具有代表性的过程特征信息。基于该特征信息建立支持向量分类机用于故障的诊断。以高压直流输电系统为例,对交流单相接地故障和直流接地故障进行诊断,诊断时间分别为12ms和11ms,诊断正确率分别为98.8%和96.8%。
|
| 关 键 词： | 粗糙集 支持向量机 故障诊断 高压直流输电 |
| 文章编号： | 1000-0054(2007)S2-1774-04 |
| 修稿时间： | 2007年4月12日 |
Fault diagnosis based on RS and SVM |
| |
| ZHANG Jianming,ZENG Jianwu,XIE Lei,WANG Shuqing.Fault diagnosis based on RS and SVM[J].Journal of Tsinghua University(Science and Technology),2007,47(Z2):1774-1777. |
| |
| Authors: | ZHANG Jianming ZENG Jianwu XIE Lei WANG Shuqing |
| |
| Abstract: | A fault diagnosis method was developed based on attribute reduction with rough set theory and principle of support vector machine classification.Rough set(RS) theory is first used to reduce the redundant information in the data.The resulting features are used to train a support vector classifier by solving a quadratic programming problem.Test results for fault detection in a high voltage direct current system show that the method has satisfactory accuracy and real time response. |
| |
| Keywords: | rough sets(RS) support vector machine(SVM) fault diagnosis high voltage direct current(HVDC) |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
