Email this article Kernel Local Fuzzy Clustering Margin Fisher Discriminant Method Faced on Fault Diagnosis
Abstract
In order to better identify the fault of rotor system,one new method based on local fuzzy clustering margin fisher discriminant (LFCMFD) was proposed. For each point on manifold, the farthest point in local neighborhood and the nearest point outside local neighborhood usually constituted the local margin. LFCMFD introduced fuzzy cluster analysis algorithm, eliminated the influence of pseudo-margin points, obtained real local margin, compute with-class scatter and between-class scatte, established local magin fisher discriminant function, found optimal fault diagnosis vector,and then identified the fault class of new testing data by this vector. In order to improve the nonlinear analysis ability of LFCMFD,considering kernel mapping idea, training data with supervision information were mapped to kernel space, constructed kernel fisher discriminant function, LFCMFD algorithm based on kernel method (KLFCMFD)was proposed. The experiment showed, KLFCMFD algorithm had best effect in comparison to other manifold learning algorithm to the rotor fault diagnosis,and fully identify fault class when selecting the appropriate parameters.
Keywords
References
[1] .H.Sebastian Seung, and Daniel D.Lee, “The manifold ways of perception”, Science, vol.290, pp.2268- 2269, December 2000.
http://dx.doi.org/10.1126/science.290.5500.2268
PMid:11188725
[2] Sam T.Roweis, and Lawrence K.Saul, “Nonlinear dimen sionality reduction by locally linear embedding”, Science, vol. 290, pp.2323- 2226, December 2000.
http://dx.doi.org/10.1126/science.290.5500.2323
PMid:11125150
[3] M.Belkin, and P.Niyogi, “Laplacian eigenmaps for dimen sionality reduction and data representation”, Science, vol. 290, pp.2323- 2226, December 2000.
PMid:11125150
[4] Z. Zhenyue, and Z. Hongyuan, “Principal manioflds and nonlinear dimension reduction via Tangent Space Alignmnet”, SIAM Journal on Scientific Computing, vol. 26, pp.313-338, January 2005.
[5] K.Olga, O.Oleg, and Matti Pietikäinen, “Supervised locally linear embedding algorithm for pattern recognition”, Pattern Recognition and Image Analysis, vol.2652, pp.386-394, December 2003.
http://dx.doi.org/10.1007/978-3-540-44871-6_45
[6] M.Belkin, and P.Niyogi, “Semi-Supervised learn- ing on riemannian manifolds”, Maching Learning, vol.56, pp.209-239, January 2004.
http://dx.doi.org/10.1023/B:MACH.0000033120.25363.1e
[7] Y. jianhong, X. jinwu, Y. debin, and Li min, “Noise reduction method for nonlinear time series based on principal manifold learning and its application to fault diagnosis”, Chinese Journal of Mechanical Engineering, Chinese, vol.45, pp.154-158, August 2006.
[8] J. quansheng, J. minping, H. jianzhong, and X. feiyun, “Method of fault pattern recognition based on laplacian eigenmaps”, Journal of System Simulation, Chinese, vol.20, pp.5710-5713, October 2008.
[9] H. Xiaofei and P.Niyogi. “Locality preserving projections”, Advances in Neural Information Processing Systems 16, cambrifge, June 2004.
[10] .W.guangbin, L.yilun, Z.xianqiong, “fault diagnosis of rolling bearings based on LLE_KFDA’, Materials Science Forum, vol. 626-627, pp. 529-534, September 2009
[11] S.Masashi, “Local fisher discriminant analysis for aupervised dimensionality reduction”, Proceedings of 23rd International Conference on Machine Learning, pp.905-912 June 2006.
[12] S.Masashi, S.Roweis, “Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis”, Machine Learning Re-search, vol.8, pp.1027-1061, 2007
[13] W.guangbin, H.liangpei, K.yuhua, “Fault diagnosis based on kernel schur-orthogonal local fisher discriminant”, chinese journal of scientific instrument, Chinese, vol.31, pp.1005- 1009, May 2010
[14] .W.guangbin, H.liangpei, K.yuquan, “Rotor Fault Diagnosis Based on Orthogonal Iteration Local Fisher Discriminant”, Journal of Vibratiion, Measurement and Diagnosis, Chinese, vol.30, pp.500- 503, October 2010
[15] W.guangbin, H.liangpei, “An improved noise reduction algorithm based on manifold learning and its application to signal noise reduction”, Applied Mechanics and Materials, vol.26-28, pp.653-656, September 2010
http://dx.doi.org/10.4028/www.scientific.net/AMM.26-28.653
Full Text: PDF