KPCA Denoising and its Application in Machinery Fault Diagnosis

Abstract:

This paper proposes a kernel principal component analysis (KPCA)-based denoising method for removing the noise from vibration signal. Firstly, one-dimensional time series is expanded to multidimensional time series by the phase space reconstruction method. Then, KPCA is performed on the multidimensional time series. The first kernel principal component is the denoised signal. A rolling bearing denoising example verify the effectiveness of the proposed method

• Periodical: Applied Mechanics and Materials (Volume 103)
• Pages: 274-278
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.103.274
• Online since: September 2011
• Authors: Ling Li Jiang, Zong Qun Deng, Si Wen Tang
• Keywords: De-Noising, Fault Diagnosis, KPCA, Rotating Machinery

References

[1] Y.W. Zhang: Chemical Engineering Science, 64(2009): 801-811.

[2] X.Q. Liu, U. Kruger, T. Littler, et al: Chemometrics and Intelligent Laboratory Systems, 96(2009): 132-143.

[3] B. Sivakumar: Journal of Hydrology, 258(2002): 149-162.

[4] Z.Y. Su, T. Wu, P.H. Yang, et al: Physica A, 387(2008): 2293-2305.

[5] A.R. Teixeira, A.M. Tome, K Stadlthanner, et al: Digital Signal Processing, 18(2008): 568-580.

[6] C. Serviere, P. Fabry: Mechanical Systems and Signal Processing, 19(2005): 1293-1311.

[7] S. Poornachandra: Digital Signal Processing, 18(2008): 49-55.

[8] Y. Xu, D. Zhang, F. X. Song, J. Y. Yang et al. : Neurocomputing, 2007, 70(4-6): 1056-1061.