文献详情
Fault diagnosis for rolling bearing based on SIFT-KPCA and SVM
文献类型期刊
作者Cheng, Yujie[1];Yuan, Hang[2];Liu, Hongmei[3];Lu, Chen[4]
机构
通讯作者Lu, C (reprint author), Beihang Univ, Sch Reliabil & Syst Engn, Beijing, Peoples R China.
来源信息年:2017  卷:34  期:1,SI  页码范围:53-65  
期刊信息ENGINEERING COMPUTATIONS影响因子和分区  ISSN:0264-4401
关键词Support vector machine; Bearing; Fault diagnosis; Kernel principal component analysis; Scale invariant feature transform
摘要Purpose - The purpose of this paper is to propose a fault diagnosis method for rolling bearings, in which the fault feature extraction is realized in a two-dimensional domain using scale invariant feature transform (SIFT) algorithm. This method is different from those methods extracting fault feature directly from the traditional one-dimensional domain. Design/methodology/approach - The vibration signal of rolling bearings is first transformed into a two-dimensional image. Then, the SIFT algorithm is applied to the image to extract the scale invariant feature vector which is highly distinctive and insensitive to noises and working condition variation. As the extracted feature vector is high-dimensional, kernel principal component analysis (KPCA) algorithm is utilized to reduce the dimension of the feature vector, and singular value decomposition technique is used to extract the singular values of the reduced feature vector. Finally, these singular values are introduced into a support vector machine (SVM) classifier to realize fault classification. Findings - The experiment results show a high fault classification accuracy based on the proposed method. Originality/value - The proposed approach for rolling bearing fault diagnosis based on SIFT-KPCA and SVM is highly effective in the experiment. The practical value in engineering application of this method can be researched in the future.
收录情况SCIE(WOS:000398271000005)  EI(20171403533775)  
所属部门可靠性与系统工程学院
DOI10.1108/EC-01-2016-0005
学科计算机:跨学科应用;工程:综合;数学跨学科应用;力学
人气指数97
浏览次数97
基金Fundamental Research Funds for the Central Universities [YWF-16-BJ-J-18]; National Natural Science Foundation of China [51575021, 51605014]; Technology Foundation Program of National Defense [Z132013B002]
全部评论(0 条评论)
作者其他论文

Prediction interval on spacecraft telemetry data based on modified block bootstrap method.

Luan, Jiahui;Tang, Jian;Lu, Chen.2010 International Conference on Artificial Intelligence and Computational Intelligence, AICI 2010.2010,6320 LNAI(PART 2),38-44.

Fault diagnosis for hydraulic pump based on EEMD-KPCA and LVQ.

Wang, Chao;Wang, Zili;Ma, Jian,等.2014,4,188-193.

Health assessment and fault diagnosis for centrifugal pumps using Softmax regression.

Ma, Jian;Lu, Chen;Zhang, Wenjin,等.JOURNAL OF VIBROENGINEERING.2014,16(3),1464-1474.

Fault detection based on RBF neural network in a hydraulic position servo system.

Liu, Hongmei;Ouyang, Pingechao;Wan, Shaoping.6th World Congress on Intelligent Control and Automation, WCICA 2006.2006,2,5708-5712.

Prediction Interval on Spacecraft Telemetry Data Based on Modified Block Bootstrap Method.

Luan, Jiahui;Tang, Jian;Lu, Chen.ARTIFICIAL INTELLIGENCE AND COMPUTATIONAL INTELLIGENCE, AICI 2010, PT II.2010,6320,38-44.

登录