Fault Prediction Based on Data Fusion

Abstract:

The performance of hydraulic pump will directly affect the normal work of the entire hydraulic system, so it is essential for its condition monitoring and fault prediction. It collects vibration signal and pressure signal for hydraulic pump which degenerates from the normal state to loose slipper state. It uses wavelet packet to decompose energy of frequency area in order to get fault feature vectors and builds support vector machine prediction model for feature vectors, then predicts possible fault by D-S evidence theory. The experiment results show that the method can effectively predict fault for hydraulic pump.

• Periodical: Advanced Materials Research (Volumes 712-715)
• Pages: 2084-2088
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.712-715.2084
• Online since: June 2013
• Authors: Hai Lei Tian, Hong Ru Li, Bao Hua Xu
• Keywords: D-S Evidence Theory, Fault Prediction, Hydraulic Pump, Support Vector Machine (SVM)

References

[1] BASIR O, YUAN X H: Information Fusion. Vol. 8(4)(2007), p.379

[2] Hong Rao, Mingfu Fu, Mingxiang Xie and Guotai Yang: China Mechanical Engineering. Vol. 20(4)(2009), p.433 (in Chinese)

[3] CHERKASSKY V, MA Y Q: Neural Networks. Vol. 17(1)(2004), p.113

[4] Dongyun Wang, Wenzhi Zhang, Jiangang Zhang: Bearing. Vol. 11(2010), p.32 (in Chinese)

[5] Bojun Chen, Mingwei Chang, Chijin Lin: IEEE Transactions on Power Systems. Vol. 19 (4) (2004), p.1821

[6] Qiang Ji, Michael M, Marefat: Pattern Recognition. Vol. 36(2003), p.1355