Fault Diagnosis of Automobile Rear Axle Based on Wavelet Packet and Support Vector Machine

Abstract:

This paper presents a fault diagnosis method of automobile rear axle based on wavelet packet analysis (WPA) and support vector machine (SVM) classifier. By Fourier transformation we find out the frequency band that can mostly reflect the rear axle failure state and use wavelet packet to decompose and reconstruct the vibration signals of rear axle, then extract each band’s energy and the variance, standard deviation, skewness, kurtosis of the specific frequency band to constitute a feature vector. We use the feature vectors which are come from some pieces of normal and abnormal samples to train support vector machine classifier for obtaining the best classification，at the same time, discuss the optimization of SVM parameters. Application shows that the method is effective in real time fault diagnosis for the automobile rear axle and has a strong anti-interference ability in different working conditions.

• Periodical: Advanced Materials Research (Volumes 211-212)
• Pages: 1021-1026
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.211-212.1021
• Online since: February 2011
• Authors: Yong Chen, Bao Qiang Wang, Jin Yao
• Keywords: Automobile Rear Axle, Fault Diagnosis, Support Vector Machine (SVM), Wavelet Packet (WP)

References

[1] Zhiping Zhang, Zhengping Liu. car rear axle quality inspection based on an average small Spectrum. China Measurement Technology, 2006. 7, 32(4): 139～140.

[2] Wenchang Zhang. Causes and diagnosis of abnormal sound for Rear Axle. Light Vehicle Technology, 2004(8) 180：49～50.

[3] Staszewski W J , Worden K, Tomilson G R. Time-frequency analysis in gearbox fault detect ion using the Wigner-Ville distribution and pat tern recognition [J ]. Mechanical System s and Signal Processing, 1997, 11(5) : 673-692.

DOI: 10.1006/mssp.1997.0102

[4] Staszewski W J , Tomilson G R. Local tooth fault detect ion in gearboxes using a moving widow procedure[ J ]. Mechanical Systems and Signal Processing, 1997, 11 (3) : 331-350.

DOI: 10.1006/mssp.1996.0087

[5] Staszewski W J , Tomilson G R. Application of wavelet transform to fault detection in spur gear [J ]. Mechanical Systems and Signal Processing, 1994, 11(3) : 289-307.

DOI: 10.1006/mssp.1994.1022

[6] Wang W J , Mcdden P D. Early detection of gear failure by vibration analysis-I: calculation of the time-frequency distribution [ J ]. Mechanical Systems and Signal Processing, 1993, 7 (3) : 193-203.

DOI: 10.1006/mssp.1993.1008

[7] Wang W J , Mcdden P D. Application of wavelets to gearbox vibration signals for fault detect ion [J ]. Journal of Sound and Vibration, 1996, 192 (5) : 927-939.

DOI: 10.1006/jsvi.1996.0226

[8] Dalpiaz G, Rivola A , Rubini R. Effectiveness and sensitivity of vibration processing techniques for local fault detection in gears [J ]. Mechanical Systems and Signal Process, 2000, 14 (3): 387-412.

DOI: 10.1006/mssp.1999.1294

[9] Byder N , Ball A. Detect ion of gear failures via vibration and acoustics signals using wavelet transform [J ]. Mechanical Systems and Signal Process, 2003, 17(4) : 787-804.

DOI: 10.1006/mssp.2001.1435

[10] Gaborson H A. The use of wavelets for analyzing transients motor current signature analysis [J ]. Sound and Vibration, 2002, 36 (9) : 12-17.

[11] Huade Wu, Wuyi Lu, Hongyun Xiong. RBF Neural Network Based Fault Diagnosis of Aircraft Engine. Changsha Aeronautical Vocational and Technical College [J]. 2005(7).

[12] Shangwei Ji. Wavelet - support vector machine fault diagnosis of rotating machinery collision. Industrial Safety and Environmental Protection Volume 36, 2010 3.

[13] Cortes C, Vapnik V. Support – Vector network[J]. Machine Learning, 1995, 20: 273-279.

[14] Vapnik V. Statistical Learning Theory [M] . Wiley, New York, NY, (1998).