Application of correlation manifold distance in the classification of rotor fault data set

doi:10.13465/j.cnki.jvs.2017.18.019

	Application of correlation manifold distance in the classification of rotor fault data set
	Zhao, Rongzhen; Zhao, Xiaoli; He, Jingju; Liu, Yunjia
	2017-09-28
发表期刊	Zhendong yu Chongji/Journal of Vibration and Shock
ISSN	10003835
卷号	36 期号:18 页码:125-130 and 139
摘要	Aiming at the difficulty in the accurate classification of rotor fault data due to a certain correlation between fault feature attribute domains, a kind of rotor fault data classification method considering the influence of the correlation coefficient was proposed. The method was based on the concept combining the correlation manifold distance marginal Fisher analysis (CDMFA) and correlation manifold distance K-nearest neighbor (CDKNN) classifier together. First of all, vibration signals were converted into high-dimensional data-set in multi-domain and multi-channel. Then, using the correlation manifold distance of the fused correlation coefficient to measure the neighbors and weights of fault samples by the CDMFA, which can better reflect the similarity relation between high-dimensional data and extract low-dimensional feature subsets to make the distance bigger between the classes. Finally, the low-dimensional feature subsets were input into the CDKNN classifier for fault pattern recognition. The proposed method was verified by using a double span rotor system data-set and simulation data-set. The results show that the method has better dimension reduction effect and higher fault classification accuracy. The study finds that the manifold distance fault data classification method can reveal more realistic geometrical relation between high-dimensional features. The method provides a theoretical reference to the data preprocessing for feature attribute reduction and classification of high dimensional fault data-set. © 2017, Editorial Office of Journal of Vibration and Shock. All right reserved.
关键词	Clustering algorithms Motion compensation Nearest neighbor search Pattern recognition Fault classification K-nearest neighbor classifiers (KNN) Manifold distance Marginal fisher analysis Rotor fault
DOI	10.13465/j.cnki.jvs.2017.18.019
收录类别	EI
语种	中文
出版者	Chinese Vibration Engineering Society
EI入藏号	20174804454428
EI主题词	Classification (of information)
EI分类号	903.1 Information Sources and Analysis - 921.5 Optimization Techniques
来源库	Compendex
分类代码	903.1 Information Sources and Analysis - 921.5 Optimization Techniques
引用统计	无
文献类型	期刊论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/114015
专题	兰州理工大学
作者单位	School of Mechanical and Electronical Engineering of Lanzhou University of Technology, Lanzhou; 730050, China
第一作者单位	兰州理工大学
第一作者的第一单位	兰州理工大学
推荐引用方式 GB/T 7714	Zhao, Rongzhen,Zhao, Xiaoli,He, Jingju,et al. Application of correlation manifold distance in the classification of rotor fault data set[J]. Zhendong yu Chongji/Journal of Vibration and Shock,2017,36(18):125-130 and 139.
APA	Zhao, Rongzhen,Zhao, Xiaoli,He, Jingju,&Liu, Yunjia.(2017).Application of correlation manifold distance in the classification of rotor fault data set.Zhendong yu Chongji/Journal of Vibration and Shock,36(18),125-130 and 139.
MLA	Zhao, Rongzhen,et al."Application of correlation manifold distance in the classification of rotor fault data set".Zhendong yu Chongji/Journal of Vibration and Shock 36.18(2017):125-130 and 139.