A Novel Denoising Method Based on Ensemble Empirical Mode Decomposition – Principle Component Analysis

Abstract:

Equipment performance degradation model is a key component in its diagnosis and prognosis models. As to slewing bearing, vibration signals are usually non-stationary and with strong white noise, which makes it very difficult to extract useful information from the signals. Therefore, an Ensemble Empirical Mode Decomposition – Principle Component Analysis (EEMD - PCA) based method was proposed to denoise the vibration signals and performance degradation model was established by PCA. To verify the proposed method, an experiment was conducted and the life cycle vibration signals were acquired. After denoising, performance degradation model was established to explain the denoising performance. Results show that the proposed method acquired a better denoising performance than EEMD-MSPCA, which provides a potential for further research.

• Periodical: Applied Mechanics and Materials (Volumes 668-669)
• Pages: 1157-1161
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.668-669.1157
• Online since: October 2014
• Authors: Yang Feng, Xiao Diao Huang*, Jie Chen, Rong Jing Hong
• Keywords: EEMD-PCA, Non-Stationary Signal, Performance Degradation Model, Slewing Bearing

References

[1] C. F. Cao, S. X. Yang, J. X. Yang: De-noising method for non-stationary vibration signals of large rotating machineries based on ensemble empirical mode decomposition, Journal of Vibration and Shock. Vol. 28 (2009), pp.33-38. (In Chinese).

[2] M. Z. Niu, J. Chen, Y. Feng, H. Wang: Wind Power Yawing Slewing Bearing Fault Diagnosis Based on Support Vector Machine, Journal of Nanjing University of Technology (Natural Science Edition). Vol. 36 (2014), pp.117-122. (In Chinese).

[3] Z. Matej, Z. Samo, P. Ivan: Multivariate and multiscale monitoring of large-size low-speed bearings using Ensemble Empirical Mode Decomposition method combined with Principal Component Analysis, Mechanical Systems and Signal Processing. Vol. 24 (2010).

DOI: 10.1016/j.ymssp.2009.09.002

[4] Z. Matej, Z. Samo, P. Ivan: Non-linear multivariate and multiscale monitoring and signal denoising strategy using Kernel Principal Component Analysis combined with Ensemble Empirical Mode Decomposition method, Mechanical Systems and Signal Processing. Vol. 25 (2011).

DOI: 10.1016/j.ymssp.2011.03.002

[5] C. Wahyu, B. K. Prabuono, K. T. Anh, et al: Condition monitoring of naturally damaged slow speed slewing bearing based on ensemble empirical mode decomposition, Journal of Mechanical Science and Technology. Vol. 27 (2013), pp.2253-2262.

DOI: 10.1007/s12206-013-0608-7

[6] Z. Wu, N. E. Huang: Ensemble empirical mode decomposition: a noise-assisted data analysis method, Advances in adaptive data analysis. Vol. 1 (2009), pp.1-41.

DOI: 10.1142/s1793536909000047

[7] L. Xu, J. M. Zhang, G. M. Zhang, et al: A Method of Rolling Bearing Fault Detection Based on PCA, Computer Simulation. Vol. 27 (2010), pp.325-329. (In Chinese).