Bearing Condition Recognition Based on Kernel Principal Component Analysis and Genetic Programming

Abstract:

In order to extract the fault feature validity in early fault diagnosis, method based on kernel principal component analysis and genetic programming (GP) is presented. The time domain features of the vibration signal are extracted and the initial symptom parameters (SP) are constructed. Then the combination to the initial SPs is carried on to optimize and build composite characteristics by GP. Through kernel principal component analysis (KPCA), the nonlinear principal component of the original characteristics is produced. Finally, the nonlinear principal components are selected as the feature subspace to classify the conditions of rolling bearing. Meanwhile, the within-class and among-class distance is introduced to compare and analyze the bearing condition recognition effect by using KPCA and GP plus KPCA separately. Experimental results show that the features extracted by kernel principal component analysis and genetic programming perform better ability in identifying the working states of the rolling bearing.

• Periodical: Applied Mechanics and Materials (Volumes 397-400)
• Pages: 1282-1285
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.397-400.1282
• Online since: September 2013
• Authors: Wen Bin Liu, Yu Xin He, Hua Qing Wang, Jian Feng Yang
• Keywords: Fault Diagnosis, Feature Extraction, Genetic Programming, Kernel Principal Component Analysis

References

[1] Koza J. R., Genetic programming: On the Programming of Computers by Means of Natural Selection, MIT Press, Cambridge, (1992).

[2] Scholkopf B and Muller K R., J. Neural Computation. 10(1998) 1299-1319.

[3] Celia C. Bojarczuk, Heitor S. Lopes, Alex A. Freitas and Edson L. Michalkiewicz, J. Artificial Intelligence in Medicine. 30(2004) 27-48.

[4] Holland J H., Adaptation in Natural and Artificial Systems, MIT Press, Cambridge, (1975).

[5] Michael D. Krames and Du Zhang: Proc. IEEE Computer Society's International Computer Software and Applications Conference, p.614, (2000).

[6] Peng Chen, Masatoshi Taniguchi, Toshio Toyota and Zhengja He, J. Mechanical Systems and Signal Processing. 19(2005) 175-194.

[7] Ji-Dong Shao, Gang Rong and Jong Min Lee, J. Chemical Engineering Research and Design. 87(2009) 1471-1480.

[8] Jiancheng Sun, Chongxun Zheng, Xiaohe Li and Yatong Zhou, IEEE Transactions on Neural Networks. 21(2010) 305-318.

DOI: 10.1109/tnn.2009.2036999