Study of Fault Diagnosis Based on Manifold Learning

Abstract:

Characteristic signals in rotating machinery fault diagnosis with the issues of complex and difficult to deal with, while the use of non-linear manifold learning method can effectively extract low-dimensional manifold characteristics embedded in the high-dimensional non-linear data. It greatly maintains the overall geometric structure of the signals and improves the efficiency and reliability of the rotating machinery fault diagnosis. According to the development prospects of manifold learning, this paper describes four classical manifold learning methods and each advantages and disadvantages. It reviews the research status and application of fault diagnosis based on manifold learning, as well as future direction of researches in the field of manifold learning fault diagnosis.

• Periodical: Applied Mechanics and Materials (Volume 312)
• Pages: 650-654
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.312.650
• Online since: February 2013
• Authors: Yi Lin He, Guang Bin Wang, Fu Ze Xu
• Keywords: Dimensionality Reduction, Fault Diagnosis, Feature Extraction, Manifold Learning

References

[1] Wang Y, Wu Y. Optimal embedding dimension estimation algorithm of Isomap. System Simulation Journal,Vol. 20-22 (2008),p .6066-6069.

[2] Meng D Y, Xu C, Xu Z B. Manifold structure reconstruction based on Isomap. Computers Journal,Vol. 33-3(2010) ,p .545-555.

DOI: 10.3724/sp.j.1016.2010.00545

[3] Zhu L, Gu Q, Cai Z H, Yu G. SMO algorithm based on Isomap and application in the coal and gas outburst prediction. Application of basic Science and Engineering,Vol. 17-6(2009) ,p .958-965.

[4] Zhang Y, Li B W. Nonlinear signal denoising approach based on the maximum variance and application in fault diagnosis. Science in China,Vol. 40-8(2010) ,p .940-945.

[5] Xiao J. Locally Linear Embedding manifold learning algorithm research and application. National defense University of Science and Technology(2005).

[6] Tan L, Wu Y, Yi D Y. Intrinsic dimension estimates based on the method of LLE(2006).

[7] Liu H H, Zhou C H. Semi-supervised Laplace feature mapping algorithm. Computer Engineering and Design, Vol. 33-2(2012),p .601-606.

[8] Jiang Q S, Jia M P, Hu J Z, Xu F Y. Fault pattern recognition method based on manifold learning(2007).

[9] Wang G B, Huang L P. A improved noise reduction algorithm based on manifold learning and its application to signal noise reduction. Applied Mechanics and Materials,Vol. 26-28(2010) ,p .653-656.

DOI: 10.4028/www.scientific.net/amm.26-28.653

[10] Yang Q, Chen G M, Tong X M, He Q F. Incremental local tangent space alignment algorithm in ball bearing fault diagnosis. Mechanical Engineering Journal,Vol. 48-5(2012) ,p .81-86.

DOI: 10.3901/jme.2012.05.081

[11] Liang L, Xu G H, Li M L, Zhang Y Z, Liang X Y. Nonlinear manifold learning method of shock fault feature extraction. Xi'an Jiaotong University (2009).

[12] Li M L, Wang S, An L L. Early bearing fault feature extraction method of nonlinear manifold learning. Xi'an Jiaotong University(2010).

[13] Andrew B, Goldberg, Xiaojin Zhu, et al. Multi- Manifold Semi-Supervised Learning. Proceedings of the 12th International Conference on Artificial Intelligence and Statistics, Florida(2009).

[14] Yong W, Yuan J, Yi W, et al. Multi-Manifold Clustering. The 11th Pacific Rlm International Conference on Artifical Intelligence, Korea . p .280-291 (2010).

[15] Min Li, Jinwu Xu, Jianhong Yang, et,al. Multiple manifolds analysis and its application to fault diagnosis.Mechanical Systems and Signal Processing, Vol. 23-8(2009) ,p .2500-2509.

DOI: 10.1016/j.ymssp.2009.05.001

[16] Huang T Q, Li K, Zhen Z. Noise supervised manifold learning algorithm. Guangxi Normal University : Natural Science ,Vol. 29-3(2011).

[17] Xiao J H. Complex equipment condition monitoring technology based on nuclear methods. Wuyi University, Vol.17-1 (2003).

[18] Wang G B, Liu Y L, Huang L P. Schur orthogonal local Fisher discriminant rotor fault diagnosis based on nuclear methods. Journal of Scientific Instrument , Vol.31-5, p .1005-1009(2010).

[19] Wang C. Supervised dimensionality reduction method based on manifold learning. University of Science and Technology of China(2009).

[20] Jiang R, Zhou J L, Lei G, Li X H. The orthogonal projection of dimensionality reduction based on supervision manifold learning . Computer Engineering, Vol.35-23(2009).

[21] Meng D Y, Xu Z B. Dai M W. A new supervised manifold learning method.Computer Research and Development,Vol. 44-12(2007), p .2072-2077.