基于粗糙核Fisher鉴别分析的特征提取及其在发动机故障诊断中的应用

胡金海; 谢寿生; 汪诚; 李应红; 杨帆

基于粗糙核Fisher鉴别分析的特征提取及其在发动机故障诊断中的应用

空军工程大学工程学院, 西安 710038

基金项目: 国家自然科学基金(60672179);军队重点科研基金(2003KJ01705)

计量
- 文章访问数: 1756
- HTML浏览量: 285
- PDF量: 485
- 被引次数: 0
出版历程
- 收稿日期: 2007-06-18
- 修回日期: 2007-10-09
- 刊出日期: 2008-07-28

Feature extraction based on rough kernel Fisher discriminant analysis and its application on aeroengine fault diagnosis

The Engineering Institute, Air force Engineering University, Xi'an, 710038, China

摘要

摘要: 将粗糙集理论的属性约简与核Fisher鉴别分析方法结合起来,提出一种基于粗糙核Fisher鉴别分析的故障特征提取方法.首先采用粗糙集理论的属性约简删除与分类无关或关系不大的特征,降低输入特征维数,排除干扰特征的影响,减小了特征提取计算量;再采用核Fisher鉴别分析方法进一步提取非线性特征;最后将该方法应用于航空发动机滑油系统故障特征提取及故障识别中.结果表明:该方法获取的特征在提高分类正确率的同时,还有效地降低了输入特征维数,提高了分类效率,并且对分类器具有较强的适应性和鲁棒性.
- 航空发动机 /
- 故障诊断 /
- 特征提取 /
- 粗糙集 /
- 核Fisher鉴别分析
Abstract: A new approach based on rough kernel fisher discriminant analysis(RKFDA) was proposed for aeroengine fault feature extraction,which combined rough set and kernel Fisher discriminant analysis.Firstly,rough set was used to exclude the features irrelevant to the fault;reduce the dimension of features,remove the effect of disturbance characteristics and cut down the cost of computation.Secondly,kernel Fisher discriminant analysis was employed on the obtained subset of features to extract the nonlinear features.Finally,fault extraction and recognition experiments in aeroengine lubricating oil system were carried out to test the performance of this method.The results show that the extracted features based on the proposed method could improve the recognition for aeroengine fault,and reduce efficiently the dimension of features with strong adaptability and robustness for various classifiers.
- aeroengine /
- fault diagnosis /
- feature extraction /
- rough set /
- kernel Fisher discriminant analysis

HTML

参考文献(11)

[1]	高秀梅.基于核投影分析的特征抽取及应用研究[D].南京:南京理工大学,2004.GAO Xiumei.Research on kernel projection analysis based feature extraction and applications[D].Nanjing:Nanjing University of Science and Technology,2004.(in Chinese)
[2]	Guo Y F,Shu T T,Yang LY,et al.Feature extraction method based on the generalized Fisher discriminant criterion and face recognition[J].Pattern Analysis & Application,2001,4(1):61-66.
[3]	李巍华,史铁林,杨叔子.基于非线性判别分析的故障分类方法研究[J].振动工程学报,2005,18(2):133-138.LI WeiHua,SHI TieLing,YANG Shuzi.Mechanical fault classification using nonlinear discriminant analysis[J].Journal of Vibration Engineering,2005,18(2):133-138.(in Chinese)
[4]	李应红,尉询楷,刘建勋.支持向量机的工程应用[M].北京:兵器工业出版社,2004.
[5]	曾黄麟.粗集理论及其应用[M].重庆:重庆大学出版社.1998.
[6]	谢忠时,李军,李晓堂,等.基于粗集理论的约简算法[J].吉林大学学报,2003,33(1):82-87.XIE Zhongshi,LI Jun,LI Xiaotang,et al.Research of reduced algorithm based on rough set theory[J].Journal of Jilin University,2003,33(1):82-87.(in Chinese)
[7]	肖健华,吴今培,樊可清,等.粗糙金成分分析在齿轮故障特征提取中的应用[J].振动工程学报,2003,16(2):166-170.XIAO Jianhua,WU Jinpei,FAN Keqing,et al.Rough principal component analysis and its application on feature extraction for gears[J].Journal of Vibration Engineering,2003,16(2):166-170.
[8]	Mika S,Ratsch G,Weston I,et al.Fisher discriminant analysis with kernels[J].In IEEE Neural Networks for Signal Processing Workshop,1999,41-48.
[9]	潘励,张祖勋,张剑清.粗集理论在图像特征选择中的应用[J].数据采集与处理,2002,17(1):42-45.PAN Li,ZHANG ZuXun,ZHANG Jianqing.Application of rough sets in image feature selection[J].Journal of Data Acquisition & Processing,2002,17(1):42-45.(in Chinese)
[10]	Bezdek J C,Pal N R.Some new index of cluster Validity[J].IEEE Trans.SMC,1998,28(3):301-315.
[11]	Hsu C W,Lin C J.A comparison of methods for multiclass support vector machines[J].IEEE Trans.Neural Netw.2002,13(2):415-425.