Class mean kernel principal component analysis and its application in fault diagnosis

被引：7
|
作者：
机构：
[1] Hunan Provincial Key Laboratory of Health Maintenance for Mechanical Equipment, Hunan University of Science and Technology
[2] Engineering Research Center of Advanced Mining Equipment of Ministry of Education, Hunan University of Science and Technology
来源：
Li, X. (hnkjdxlxj@163.com) | 1600年 / Chinese Mechanical Engineering Society卷 / 50期
关键词：
Class mean kernel principal component analysis; Fault diagnosis; Kernel principal component analysis;
D O I：
10.3901/JME.2014.03.123
中图分类号：
学科分类号：
摘要：
In the application of kernel principal component analysis, cumulative contribution rate method is used to determine the number of kernel principal component usually, which abandon some kernel principal components whose contribution rate is small. It loses part information of samples and influences fault diagnosis effect. Aiming at this fact, a kernel principal component analysis method based on class mean is proposed. After data samples in input space are mapped into higher-dimensional space, class mean vectors of mapped data are determined, and then the PCA method is used to analyze the class mean vectors in the subspace of class mean vectors. Construct class mean kernel matrix, and make use of it to construct algorithm of class mean kernel principal component. The feature vectors formed by class mean kernel principal component include all variable information of initial data and its dimension is lower than the number of fault category. It can realize dimensionality reduction without information loss based on class mean vector. The improved algorithm is applied to rolling bearing fault diagnosis, and the results show that it has the stronger ability of integrating original variable information than KPCA, which can extract classified information of data samples more effectively and recognize fault accurately. © 2014 Journal of Mechanical Engineering.
引用
收藏
页码：123 / 129
页数：6
相关论文
共 14 条
  • [1] Jolliffe I.T., Principal Component Analysis, (2002)
  • [2] Scholkopf B., Smola A., Muller K.R., Nonlinear component analysis as a kernel eigenvalue problem, Neural Computation, 10, 5, pp. 1299-1319, (1998)
  • [3] Zvokelj M., Zupan S., Prebil I., Non-linear multivariate and multiscale monitoring and signal denoising strategy using kernel principal component analysis combined with ensemble empirical mode decomposition method, Mechanical Systems and Signal Processing, 25, 7, pp. 2631-2653, (2011)
  • [4] Issam B.K., Mohamed L., Claus W., Variable window adaptive kernel principal component analysis for nonlinear nonstationary process monitoring, Computers and Industrial Engineering, 61, 3, pp. 437-446, (2011)
  • [5] Wang L., Wang F., Zhu H., Et al., Empirical-mode decomposition based on kernel principal component analysis with application, Journal of Vibration and Shock, 29, 2, pp. 39-41, (2010)
  • [6] Li T., Yi J., Su Y., Et al., Variable selection for nonlinear modeling based on false nearest neighbours in kpca subspace, Journal of Mechanical Engineering, 48, 10, pp. 192-198, (2012)
  • [7] Sun C., He Z., Zhang Z., Et al., Operating reliability assessment for aero-engine based on condition monitoring information, Journal of Mechanical Engineering, 49, 6, pp. 30-37, (2013)
  • [8] Jiang W., Wu S., Liu S., Exponentially weighted dynamic kernel principal component analysis algorithm and its application in fault diagnosis, Journal of Mechanical Engineering, 47, 3, pp. 63-68, (2011)
  • [9] Zhang Y., Zhou H., Qin S.J., Decentralized fault diagnosis of large-scale processes using multiblock kernel principal component analysis, Acta Automatica Sinica, 36, 4, pp. 593-587, (2010)
  • [10] Wei Y., Matrix-based kernel method for large-scale data set, International Journal of Image, Graphics and Signal Processing, 2, pp. 1-10, (2010)
12