Partial Friction Fault Diagnosis of Electrical Submersible Pump Based on Support Vector Machines

Abstract:

Exact diagnosis of electrical submersible pump （ESP）partial friction fault may avoid magnitude economic loss. Three-dimensional vibration accelerations of ESP were measured with acceleration transducer. Since working well ESPs are deeper in the earth, vibration signals seriously fade. This paper proposed that SVM is employed as classifier and wavelet parameters as features for ESP partial friction fault diagnosis. After SVM parameters selection with grid method, the highest recognition rate is up to 86.7%. Results indicate that SVM is competent not only for small sample recognitions but also for recognitions based on faintness signal. A new method is provided for ESP partial friction fault diagnosis.

• Periodical: Advanced Materials Research (Volumes 219-220)
• Pages: 1689-1692
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.219-220.1689
• Online since: March 2011
• Authors: Cheng Yao, Ming Zhong Li, Guang Fu Liu
• Keywords: Acceleration, Faintness Signal, Support Vector Machine (SVM), Vibration, Wavelet Transform (WT)

References

[1] Feng Ding, Zhu Hongwu, Xue Dunsong. Synthetic diagnosis model for electric submersible pump unit based on system analysis [J]. Acta Petrolei Sinica, 2007, 28(1):127-130.

[2] Zhang Mingjun, Dong Zhengang, Zhang Bingliang. Status montoring of electric submersible pump and down hole sensors [J]. Electric Machines and Control, 2009, 13(1):28-33.

[3] Feng Ding, Li Chengjian, Zhu Hongwu, et al. Study of Electric Submersible Pump Vibration Caused to Invalidation [J]. Journal of Oil and Gas Technology, 2005, 27(8):519-521.

[4] Fan Yongsheng．Modern Signal Processing Method of Mechanical Equipment Diagnosis [M]．Beijing : National Defence Industry Press, 2009.

[5] Chiranjib Koley, Prithwiraj Purkait, Sivaji Chakravorti. Wavelet-Aided SVM Tool for Impulse Fault Identification in Transformers [J]. IEEE Transactions on Power Delivery, 2006,21（2）:1-8.

DOI: 10.1109/tpwrd.2005.860255

[6] Ozgonenel Okan, Kilic Erdal, Thomas David, et al. Identification of transformer internal faults by using an RBF network based on dynamical principle component analysis[C]. International Conference on Power Engineering, Energy and Electrical Drives. USE: IEEE, 2007: 719-724.

DOI: 10.1109/powereng.2007.4380215

[7] Xiong Chunrong, Huang Wenming, Li Meijin, et al. Research on License Plate Character Recognition Based on Character characteristic and Support Vector Machine[J] . Techniques of Automation & Applications, 2010,29(1): 64-66.

[8] Rojas, A., & Nandi, A. K.. Practical scheme for fast detection and classification of rolling-element bearing faults using support vector machines[J]. Mechanical Systems and Signal Processing, 2006,20 :1523–1536.

DOI: 10.1016/j.ymssp.2005.05.002

[9] Sugumaran, V., Muralidharan, V., & Ramachandran, K. I. Feature selection using decision tree and classification through proximal support vector machine for fault diagnostics of roller bearing[J]. Mechanical Systems and Signal Processing, 2007, 21 :930–942.

DOI: 10.1016/j.ymssp.2006.05.004