Gear Incipient Diagnosing Based on EEMD and Genetic-Support Vector Machine

Abstract:

Due to the incipient fault attributes of gear are not obvious, So a hybrid diagnosis model to gear diagnosing based on Ensemble Empirical Mode Decomposition (EEMD) and Genetic-Support Vector Machine (GSVM) was proposed. With the method of EEMD,the gear vibration signals are adaptively decomposed into a finite number of Intrinsic Mode Function (IMF),which can alleviate model mixing that may appear in conventional EMD method. It calculates the energy character vectors of every IMF components,energy feature extracted from a number of IMFs that contained the most dominant fault information could serve as input genetic-vectors of support vector machine. The proposed model is applied to the gear testing system, and the results show that the diagnosis approach was effectively.

• Periodical: Applied Mechanics and Materials (Volumes 397-400)
• Pages: 2104-2110
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.397-400.2104
• Online since: September 2013
• Authors: Cheng Yong Xiao, Bo Qiang Shi, Zhi Jun Hao, Shuang Ming Zhu
• Keywords: Ensemble Empirical Mode Decomposition, Fault Diagnosis, Gear, Genetic Algorithm (GA), Support Vector Machine (SVM)

References

[1] G. Meltzer N.P. Dien, Fault diagnosis in gears operating under non-stationary rotational speed using polar wavelet amplitude maps，Mechanical Systems and Signal Processing, 2004, 18(5): 985-992.

DOI: 10.1016/j.ymssp.2004.01.009

[2] W.J. Stasxewski, K. Wordcn, G.R. Tomlinson, Time-frequency analysis in gearbox fault detections using the Wigner-Ville distribution and pattern recognition, Mechanical System and Signal Processing, 1997，11: 673-692.

DOI: 10.1006/mssp.1997.0102

[3] S.J. Loutridis, Damage detection in gear systems using empirical made decomposition, Engineering Structures, 2004, 26: 1833-1841.

DOI: 10.1016/j.engstruct.2004.07.007

[4] WU Zhao-hua, HUANG Norden E. Ensemble empirical mode decomposition: A noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1(1): 1−41.

DOI: 10.1142/s1793536909000047

[5] Lue CHEN, Yanyang ZI, Zhengjia HE, CHENG Wei. Research and Application of Ensemble Empirical Mode Decomposition Principle and 1. 5 Dimension Spectrum Method. Journal of Xi'an Jiao Tong University[J], 2009, 43(5): 94-98(In Chinese).

[6] Jian Zhang, Ruqiang Yan, Robert X. Gao, Zhihua Feng. Performance enhancement of ensemble empirical mode decomposition, Mechanical Systems and Signal Processing, 2010, 24: 2104～2133.

DOI: 10.1016/j.ymssp.2010.03.003

[7] Zheng-jia. Multi-Fault Classifier Based on Support Vector Machine and Its Applications[J]. Mechanical Science and Technology, 2004, 23(5): 537-540.