Abstract
A new approach is proposed to construct a reasonable prediction model for prognostic. The Gaussian mixture model-based health indicator is used for degradation performance and help to determine the threshold of the incipient fault. The support vector regression is joined with least mean square algorithm for the construction of the adaptive prediction model based on the historical data and the online monitoring data. According to the failure threshold, the remaining life can be obtained. Through experimental verification, the results show that the selected health index is able to effectively reflect the degradation of rolling bearings, and the proposed model shows great prediction accuracy in comparison to the common one.
Similar content being viewed by others
References
H. Qiu, J. Lee, J. Lin et al., Robust performance degradation assessment methods for enhanced rolling element bearing prognostics. Adv. Eng. Inform. 17(3), 127–140 (2003)
R. Huang, L. Xi, X. Li et al., Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods. Mech. Syst. Signal Process. 21(1), 193–207 (2007)
A.K. Mahamad, T. Hiyama, Fault classification based artificial intelligent methods of induction motor bearing. Int. J. Innov. Comput. Inf. Control 7(9), 5477–5494 (2011)
Z. Tian, An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring. J. Intell. Manuf. 23(2), 227–237 (2012)
S. Goyal, G.K. Goyal, A new scientific approach of intelligent artificial neural network engineering for predicting shelf life of milky white dessert jeweled with pistachio. Int. J. Sci. Eng. Res. 2(9), 1–4 (2011)
Z. Tian, L. Wong, N. Safaei, A neural network approach for remaining useful life prediction utilizing both failure and suspension histories. Mech. Syst. Signal Process. 24(5), 1542–1555 (2010)
M.E. Orchard, G.J. Vachtsevanos, A particle-filtering approach for on-line fault diagnosis and failure prognosis. Trans. Inst. Meas. Control 31(3–4), 221–246 (2009)
M.E. Orchard, G.J. Vachtsevanos, A particle filtering approach for on-line failure prognosis in a planetary carrier plate. Int. J. Fuzzy Logic Intell. Syst. 7(4), 221–227 (2007)
D.A. Tobon-Mejia, K. Medjaher, N. Zerhouni, CNC machine tool’s wear diagnostic and prognostic by using dynamic Bayesian networks. Mech. Syst. Signal Process. 28, 167–182 (2012)
S. Hong, Z. Zhou, Remaining useful life prognosis of bearing based on Gauss process regression[C]//Biomedical Engineering and Informatics (BMEI) 5th International Conference on IEEE, 2012: 1575–1579, 2012
S. Hong, Z. Zhou, Application of Gaussian process regression for bearing degradation assessment[C]//Information Science and Service Science and Data Mining (ISSDM), 6th International Conference on New Trends in IEEE, 2012: 644–648, 2012
J. Yu, Bearing performance degradation assessment using locality preserving projections and Gaussian mixture models. Mech. Syst. Signal Process. 25(7), 2573–2588 (2011)
D. Basak, S. Pal, D.C. Patranabis, Support vector regression. Neural Inf. Process. 11(10), 203–224 (2007)
J. Yan, C. Guo, X. Wang, A dynamic multi-scale Markov model based methodology for remaining life prediction. Mech. Syst. Signal Process. 25(4), 1364–1376 (2011)
Acknowledgments
The work described in this paper was supported by a grant from the National Defense Researching Fund (No. 9140A27020413JB11076).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, Xl., Gu, H., Xu, L. et al. A SVR-Based Remaining Life Prediction for Rolling Element Bearings. J Fail. Anal. and Preven. 15, 548–554 (2015). https://doi.org/10.1007/s11668-015-9976-x
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11668-015-9976-x