1551. Remaining useful life prediction of rolling bearings by the particle filter method based on degradation rate tracking

Bin Fan1, Lei Hu2, Niaoqing Hu3

Science and Technology on Integrated Logistics Support Laboratory,
National University of Defense Technology, Changsha 410073, P. R. China

2Corresponding author

E-mail: 1fanbin85510@163.com, 2lake_hl@hotmail.com, 3hnq@nudt.edu.cn

(Received 9 December 2014; received in revised form 7 February 2015; accepted 10 March 2015)

Abstract. There is no doubt that remaining useful life prediction is important to the health management of modern mechanical equipment. But in most cases, the useful operational information of equipment we can get are limited, one of them is vibration signal. Particle filter is a hybrid prediction method combined with data-driven and model-based two kinds of methods. It can solve prognosis problem with the fitted prediction model only by historical data, and allow the uncertainty management. However, the prediction performance of the method is largely dependent on the prediction model and very sensitive to the initial distribution of the model parameters. These flaws limit the further development of particle filter methods in the prediction. Aiming at the shortcomings of the basic particle filter prediction method, a general prediction framework of particle filter based on degradation rate tracking is proposed in this paper. It turned away from the fitted model, and utilized the statistical rule of degradation rate of historical data to estimate and predict the degradation process of system. The effectiveness of the method proposed is validated with useful life prediction case of rolling bearings.

Keywords: particle filter, vibration signal, degradation rate tracking, rolling bearing, remaining useful life prediction.

References

[1]        Kruzic J. J. Predicting fatigue failures. Science, Vol. 325, 2009, p. 156‑157.

[2]        Yogesh G. B., Ibrahim Z., Sagar V. K. Overview of remaining useful life methodologies. ASME 2008 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, American Society of Mechanical Engineers, New York, ASME, 2008, p. 1391‑1400.

[3]        Shao Y., Nezu K. Prognosis of remaining bearing life using neural networks. Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, Vol. 214, Issue 3, 2000, p. 217‑230.

[4]        Lee J. A similarity-based prognostics approach for remaining useful life estimation of engineered systems. IEEE International Conference on Prognostics and Health Management, Denver, 2008, p. 1‑6.

[5]        Dong M., He D. A segmental hidden semi-Markov model-based diagnostics and prognostics framework and methodology. Mechanical Systems and Signal Processing, Vol. 21, Issue 5, 2007, p. 2248‑2266.

[6]        Di Maio F., Tsui K. L., Zio E. Combining relevance vector machines and exponential regression for bearing residual life estimation. Mechanical Systems and Signal Processing, Vol. 31, 2012, p. 405‑427.

[7]        Li C. J., Lee H. Gear fatigue crack prognosis using embedded model, gear dynamic model and fracture mechanics. Mechanical Systems and Signal Processing, Vol. 19, Issue 4, 2005, p. 836‑849.

[8]        Feng Z., Zuo M. J., Chu F. Application of regularization dimension to gear damage assessment. Mechanical Systems and Signal Processing, Vol. 24, 2010, p. 1081‑1098.

[9]        Orchard M. E. A Particle Filtering-Based Framework for On-Line Fault Diagnosis and Failure Prognosis. Dissertation for the Doctoral Degree, Atlanta, Georgia Institute of Technology, 2007.

[10]     Zio E., Peloni G. Particle filtering prognostic estimation of the remaining useful life of nonlinear components. Reliability Engineering and System Safety, Vol. 96, Issue 3, 20011, p. 403‑409.

[11]     Jin G., Matthews D. E., Zhou Z. A Bayesian framework for on-line degradation assessment and residual life prediction of secondary batteries in spacecraft. Reliability Engineering and System Safety, Vol. 113, 2013, p. 7‑20.

[12]     Saha B., Goebel K. Uncertainty management for diagnostics and prognosticsof batteries using bayesian techniques. IEEE Aerospace Conference, 2008, p. 1‑8.

[13]     He W., Williard N., Osterman M., Pecht M. Prognostics of lithium-ion based on Dempster-Shafer theory and the Bayesian Monte Carlo method. Journal of Power Sources, Vol. 196, 2011, p. 10134‑10321.

[14]     Chen C., Pecht M. Prognostics of lithium-ion batteries using model-based and data-driven methods. IEEE International Conference on Prognostics and Health Management, Denver, 2012, p. 1‑6.

[15]     Wang D., Miao Q., Pecht M. Prognostics of lithium-ion batteries based on relevance vectors and a conditional three-parameter capacity degradation model. Journal of Power Sources, Vol. 239, 2013, p. 253‑264.

[16]     Gordon N. J., Salmond D. J., Smith A. F. M. Novel approach to nonlinear/non-gaussianbayesian state estimation. IEE Proceedings on F Radar and Signal Processing, Vol. 140, Issue 2, 1993, p. 107‑113.

[17]     Carpenter J., Clifford P., Fearnhead P. Improved particle filter for nonlinear problems. IEE Proceedings on Radar, Sonar and Navigation, Vol. 146, Issue 1, 1999, p. 2‑7.

[18]     http://www.femto-st.fr/en/Research-departments/AS2M/Research-groups/PHM/IEEE-PHM-2012-Datachallenge.php.

[19]     Fan X. H., An G., Wang K., Wu D. M. Research on vibration severity for machine condition monitoring. Journal of Academy of Armored Force Engineering, Vol. 22, Issue 4, 2008, p. 46‑49, (in Chinese).

Cite this article

Fan Bin, Hu Lei, Hu Niaoqing Remaining useful life prediction of rolling bearings by the particle filter method based on degradation rate tracking. Journal of Vibroengineering, Vol. 17, Issue 2, 2015, p. 743‑756.

 

JVE International Ltd. Journal of Vibroengineering. Mar 2015, Volume 17, Issue 2. ISSN 1392-8716