The Fault Diagnosis Method for Roller Bearing with Harmonic Wavelet Packet and DT-SVM

Abstract:

This paper studies the roller bearing fault diagnosis method with harmonic wavelet packet and Decision Tree-Support Vector Machine (DT-SVM). The harmonic wavelet packet possesses better performances for its box-shaped spectrum and unlimited subdivision compared with the conventional time-frequency feature exaction method. Firstly, the proposed method decomposes the roller bearing vibration signal with harmonic wavelet packet and extracts the feature energy with coefficients of each spectrum. After the feature energy is normalized, feature vector are available. Based on multi-level binary tree, this paper designs the multi-classification SVM model due to its superior nonlinear mapping capability. Three two-classifications are incorporated to diagnosis the roller bearing faults. Finally, the proposed method is illustrated with the vibration data from the roller bearing stand of electric engineering lab in case western reserve university. Experimental results illustrate the higher accuracy of the proposed method compared with conventional method.

• Periodical: Applied Mechanics and Materials (Volume 724)
• Pages: 238-241
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.724.238
• Online since: January 2015
• Authors: Rui Pan, Tao Xu*, Yong Liu
• Keywords: Fault Diagnosis, Harmonic Wavelet Packet, Roller Bearing, Support Vector Machine (SVM)

References

[1] REN Ling-zhi, YU De-jie, PENG Fu-qiang. Generalized Demodulation Method Based on Multi-scale Chirpelt and Sparse Signal Decomposition and Its Application to Roller Bearing Fault Diagnosis. Proceeding of the CSEE. Vol. 30(2010).

DOI: 10.3901/jme.2010.15.059

[3] Duan H., Gantam A., Shaw B. D., et al. Harmonic wavelet analysis of modulated tunable diode laser 3absorption spectroscopy signals. Applied Optics. Vol. 48(2009), pp.401-407.

DOI: 10.1364/ao.48.000401

[4] Wang Zhigang, Li Yourong, Li Fang. Fault Diagnosis Method based on Harmonic Wavelet Analysis. JOURNAL OF VIBRATION AND SHOCK. Vol. 25(200), pp.125-128 (in Chinese).

[5] NEWLAND D E. Wavelet analysis of vibration, part 1: Theory[J]. Journal of Vibration and Acoustics, 1994, 116: 409-416.

DOI: 10.1115/1.2930443

[6] Yu Jintao, Ding Mingli, Meng Fangang, et al. Acoustic emission source identification based on harmonic wavelet packet and support vector machine. Journal of Southeast University (English Edition). Vol. 27(2011), pp.300-304.

[7] WU Yiquan, SONG Yu, ZHOU Huaichun. State Identification of Boiler Combustion Flame Image Based on Grey Entropy Multiple Thresholding and Support Vector Machine. Proceeding of CSEE. Vol. 33(2013), pp.66-73 (in Chinese).

[8] HSU C. W., LIN C. J. A comparison of methods for multi-class support vector machine. IEEE Transactions on Neural Network. Vol. 13(2002), pp.415-425.

[9] Information on http: /csegroups. case. edu/bearingdatacenter/pages/download-data-file.