Rolling Bearing Fault Diagnosis Based on Wavelet Packet and Improved BP Neural Network for Wind Turbines

Abstract:

Vibration signal was a carrier of fault features of the wind turbine transmission system, it can reflect most of the fault information of the wind turbine transmission system. According to the frequency domain features of the roller bearing fault, wavelet packet transform for feature extraction was proposed as the characteristics of wind turbines in the presence of a large number of transient and non-stationary signals. The characteristics of wavelet packet was analyzed, combined with the wind turbines in the rolling bearing fault characteristic vibration extraction methods, the rolling bearing fault diagnosis was realized through the wavelet packet decomposition and reconstruction, the procedure was given. The simulation result shows that this application can reflect relationship of the failure characteristics and frequency domain feature vectors, also the nonlinear mapping ability of neural networks was played and the fault diagnosis capability enhanced.

• Periodical: Applied Mechanics and Materials (Volumes 347-350)
• Pages: 117-120
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.347-350.117
• Online since: August 2013
• Authors: Zhao Ran Hou
• Keywords: Fault Diagnosis, Feature Extraction, Rolling Bearing, Vibration Characteristic, Wavelet Packet

References

[1] SUN Wei, XIONG Bang-shu, HUANG Jian-ping, MO Yan. Fault diagnosis of a rolling bearing using wavelet paceet de-noising and LMD. JOURNAL OF VIBRATION AND SHOCK, 2012(18): 153-156.

[2] YANG Jianwei, CAI Guoqiang, YAO Dechen, etc. Fault diagnosis method for the rolling bearing of railway vehicle based on wavelet packet transform and BP neural network[J]. CHINA RAILWAY SCIENCE, 2010, 31(6): 68-73.

DOI: 10.1109/cason.2010.161

[3] WANG WU. Simulation of Mobile Welding Robot with Variable Structure Control. 2010 Asia-Pacific Conference on Innovative Computing and Communication, Information Technology and Ocean Engineering (CICC-ITOE 2010) , 2010, pp.106-109.

DOI: 10.1109/cicc-itoe.2010.35

[4] LIU Haibo, YANG Jianwei, CAI Guoqiang, etc. Fault diagnosis of bearing based on the wavelet package and RBF neural network[J]. Machine Design and Research, 2010, 26(2): 92-94.

[5] WANG Wu, ZHANG Yuan-min, WANG Hong-ling. Application of sensitivity pruning neural networks in surface roughness prediction[J]. 2009 Second International Conference on Intelligent Computation Technology and Automation, 2009, pp.48-51.

DOI: 10.1109/icicta.2009.20

[6] TAN Xun-qiong, TANG Jie, WU Zheng-qiu . 10 MW variable speed direct-driven wind turbines modeling and Matlab simulation [J]. Power System Protection and Control, 2011, 39(24): 31-37.

[7] Wang Wu, Su Liang-yu. Application of CMAC-PID Compound Control in PMLSM Servo System[J]. Advanced Materials Research Vols. 341-342(2012), pp.780-784.

DOI: 10.4028/www.scientific.net/amr.341-342.780

[8] WANG Wu, TANG San, ZHANG Yuan-min. Prediction of surface roughness of high speed machining based on neural networks. Machinery Design & Manufacture. 2010, (3): 216-217.