A Method of False Component Discriminant of EMD Based on Kolmogorov-Smirnov Test

Abstract:

In order to solve the problem that empirical mode decomposition (EMD) will cause false components in the process of signal decomposition, a method of false component discriminant of EMD based on Kolmogorov-Smirnov test was put forward. First, the original signal was decomposed into several intrinsic mode functions (IMFs) by EMD. Then the K-S test was used to calculate the similarity between each IMF and the original signal. The reasonable similarity threshold was selected for judging the authenticity of the IMFs. The IMFs of which the similarity values were less than the threshold value were determined to be the false components. The others of which the similarity values were greater than the threshold value were determined to be the real components. As a result, the false components were removed and the real components were remained. The vibration signal of bearing experiment indicated that the method of K-S test could discriminate the real components and the false components obviously. Then the false components were removed quickly and accurately and the real components of the original signal were obtained.

• Periodical: Applied Mechanics and Materials (Volumes 427-429)
• Pages: 2005-2008
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.427-429.2005
• Online since: September 2013
• Authors: Wang Can Yang*, Pei Lin Zhang, Ding Hai Wu, Zhou Xin
• Keywords: Empirical Mode Decomposition (EMD), False Component, K-S Test, Similarity, Vibration Signal

References

[1] Huang N E, Shen Z, Long S R. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London, 1998, 454 (1): 903-995.

DOI: 10.1098/rspa.1998.0193

[2] Julien Fleureau, Amar Kachenoura, Laurent Albera, et al. Extraction of time varying information from noisy signals: An approach based on the empirical mode decomposition[J]. Mechanical Systems and Signal Processing, 2011, 91: 2783-2792.

DOI: 10.1016/j.sigpro.2011.01.018

[3] DENG Jian-xun, XIONG Zhong-yang, ZENG Dai-min. Face Recognition Based on Improved Fast EMD-MIL Framework and Information Fusion[J]. Journal of Sichuan University, 2012, 44 (2): 99-104.

[4] ZHANG Zhi-gang, SHI Xiao-hui, CHEN Zhe-ming, et al. Fault feature extraction of rolling element beating based on improved EMD and sliding kurtosis algorithm[J]. Journal of Vibration and Shock, 2012, 31 (22): 80-83.

[5] CAI Yan-ping, LI Ai-hua, WANG Tao, et al. I.C. engine vibration time-frequency analysis based on EMD-Wigner-Ville[J]. Journal o f Vibration Engineering, 2010, 23 (4): 430-437.

[6] ZHAO Xuan-min, XU Wei, SHI Yi-min, et al. Mathematical Statistics[M]. Beijing: science publishing house, (2005).