Fault Recognition of Gear Pump Based on EMD Neural Network

Abstract:

Aim at the non-stationary and time-variation characteristic of the gear-pump fault signal, proposing a condition recognition method for gear pump based on EMD and neural network. Take the vibration acceleration of case as the analysis object. Firstly,deal the signal with EMD, extract the main IMF components, containing the main information components. And then calculate its energy, and use the energy ratio to compose the feature vectors , which is used for BP neural network to identify the gear pump working state. The result reveals the EMD neural network method can recognize the working conditions of mesh-type high-pressure gear pump CB-KP63.

• Periodical: Applied Mechanics and Materials (Volumes 333-335)
• Pages: 1635-1639
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.333-335.1635
• Online since: July 2013
• Authors: Shu Xiang Gao, Xiao Hu Chen, Yao Ding
• Keywords: Empirical Mode Decomposition (EMD), Energy Ratio, Gear Pump, Neural Network (NN)

References

[1] Nie Songlin, Shi Xueyuan, Hu Bin, et. al. Simulation on Status of Hydraulic Contamination and Optimum Collocation of Hydraulic Filters in Hydraulic System. Proceeding of ISTP'2007. 2007. 1053-1056.

[2] XIAO Tibing, JIANG Xingping, Ling Ling, et. Modeling and Simulation of Hydraulic System of the Beam Part of the Tile Press Based on AMEsim. IEEE, 2011. 593-596.

DOI: 10.1109/fpm.2011.6045832

[3] Fu Yongling, Qi Xiao Ye. AMESim System Modeling and Simulation-From Novice to Professional [M]. Beijing: Beijing Aerospace University Press, (2006).

[4] Fu Yongling, Fan Dianliang, Qi Haitao. The Application of Co-Simulation Based on AMESim and Matlab in Electro-hydraulic Servo System. 2011 International Conference on Electronic & Mechanical Engineering and Information Technology. 2011. 3547-3550.

DOI: 10.1109/emeit.2011.6023061

[5] Zhang L. X., The Load Simulator Using Blow Servo Valve with Interconnected Pores[C]. Proceedings of Third China-Russia-Ukraine Symposiumon Astronautical Science and Technology, Xi'an. 1994, (9): 652-655.

[6] Wang W. H., Hou Z. S., Jin S. T., Model-Free Indirect Adaptive Decoupling Control for Nonlinear Discrete-Time MIMO Systems[C], IEEE Conference on Decision and Control & Chinese Control Conference 09, Dec. 16-18, 2009, shanghai, CHINA, 7663-7668.

DOI: 10.1109/cdc.2009.5400164

[7] Qi Haitao, Fu Yongling, Simulation of Electro-hydrostatic Actuator Based on AMESim [J]. Machine tool & hydraulics, 2007, 35(3): 184-186.

[8] Xing Keli, Feng Yu, Jin Xiajie, Li Qing. Simulation of Electrohydraulic Servo System Based on AMESim/Matlab [J]. Machine Tool & Hydraulics, 2004, 10: 57~58.

[9] Wan Lixiang, Ding Baohua, Zhou Zhou, Xu Jun. Study onDynamical Simulation of Hydraulic Servo System Based on AMESim and Simulink [J]. Coal Mine Machinery, 2007, 9：40~42.

[10] Gu Hairong, Wang Yongqi, Tao Wei, Fang Liwen. Hydraulic system simulation of hydrostatic bulldozer based on AMESIM [J]. Road Machinery & Construction Mechanization, 2005, 1: 47~49.