1547. Bearing remaining life prediction using Gaussian process regression with composite kernel functions

Sheng Hong1, Zheng Zhou2, Chen Lu3, Baoqing Wang4, Tingdi Zhao5

1, 3, 4, 5Science and Technology on Reliability and Environmental Engineering Laboratory,
School of Reliability and System Engineering, Beihang University, Beihang, China

2Systems Engineering Research Institute, China State Shipbuilding Corporation (CSSC), Beijing, China

1, 3Corresponding authors

E-mail: 1shenghong@buaa.edu.cn, 3luchen@buaa.edu.cn

(Received 20 March 2014; received in revised form 30 January 2015; accepted 20 February 2015)

Abstract. There is an urgent demand for life prediction of bearing in industry. Effective bearing degradation assessment technique is beneficial to condition based maintenance (CBM). In this paper, Gaussian Process Regression (GPR) is used for remaining bearing life prediction. Three main steps of prediction schedule are presented in details. RMS, Kurtosis and Crest factor are used for feature fusion by self-organizing map (SOM). Minimum Quantization Error (MQE) value derived from SOM is applied to represent the condition of bearing. GPR models with both single and composite covariance functions are presented. After training, new MQE value can be predicted by the GPR model according to previous data points. Experimental results show that composite kernels improve the accuracy and reduce the variance of prediction results. Compared with particle filter (PF), GPR model can predict the remaining life of bearings more accurately.

Keywords: Gaussian process regression, uncertainty distribution, bearing life prediction.


[1]        Heng A., Zhang S., Tan A. C. C. Rotating machinery prognostics: State of the art, challenges and opportunities. Mechanical Systems and Signal Processing, Vol. 23, Issue 3, 2009, p. 724-739.

[2]        Qiu H., Lee J., Lin J. Robust performance degradation assessment methods for enhanced rolling element bearing prognostics. Advanced Engineering Informatics, Vol. 17, Issue 3, 2003, p. 127-140.

[3]        Pan Y., Chen J., Guo L. Robust bearing performance degradation assessment method based on improved wavelet packet‑support vector data description. Mechanical Systems and Signal Processing Vol. 23, Issue 3, 2009, p. 669-681.

[4]        Huang R., Xi L., Li X., Richard C., Qiu H., Lee J. Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods. Mechanical Systems and Signal Processing, Vol. 21, Issue 1, 2007, p. 193-207.

[5]        Gebraeel N., Lawley M., Liu R. Residual life predictions from vibration-based degradation signals: a neural network approach. IEEE Transactions on Industrial Electronics, Vol. 51, Issue 3, 2004, p. 694‑700.

[6]        Mahamad A. K., Saon S., Hiyama T. Predicting remaining useful life of rotating machinery based artificial neural network. Applied Mathematics and Computation, Vol. 60, Issue 4, 2010, p. 1078‑1087.

[7]        Wang P., Vachtsevanos G. Fault prognostics using dynamic wavelet neural networks. Ai Edam‑Artificial Intelligence for Engineering Design Analysis and Manufacturing, Vol. 15, Issue 4, 2001, p. 349-365.

[8]        Sun C., Zhang Z., He Z. Research on bearing life prediction based on support vector machine and its application. Journal of Physics: Conference Series, Vol. 305, Issue 1, 2011, p. 12-28.

[9]        Caesarendra W., Widodo A., Yang B. Application of relevance vector machine and logistic regression for machine degradation assessment. Mechanical Systems and Signal Processing, Vol. 24, Issue 4, 2010, p. 1161-1171.

[10]     Saha S., Saha B., Goebel K. A distributed prognostic health management architecture. Proceedings of the Conference of the Society for Machinery Failure, 2009.

[11]     Saha S., Saha B., Saxena A., Goebel K. Distributed prognostic health management with gaussian process regression. IEEE Aerospace Conference, 2010, p. 1-8.

[12]     Liu K., Liu B., Xu C. Intelligent analysis model of slope nonlinear displacement time series based on genetic-Gaussian process regression algorithm of combined kernel function. Chinese Journal of Rock Mechanics and Engineering, Vol. 10, 2009, p. 2128-2134.

[13]     Rasmussen C. E., Williams C. K. I. Gaussian Processes for Machine Learning. MIT Press Cambridge, MA, 2006.

[14]     Mortada M., Yacout S., Lakis A. Diagnosis of rotor bearings using logical analysis of data. Journal of Quality in Maintenance Engineering, Vol. 17, Issue 4, 2011, p. 371-397.

[15]     Hong S., Zhou Z., Zio E., Hong K. Condition assessment for the performance degradation of bearing based on a combinatorial feature extraction method. Digital Signal Processing, Vol. 27, 2014, p, 159‑166.

[16]     Kohonen T. Self-Organizing Maps. Springer, 1995.

[17]     Jamsa-Jounela S., Vermasvuori M., Enden P., Haavisto S. A process monitoring system based on the Kohonen self-organizing maps. Control Engineering Practice, Vol. 11, Issue 1, 2003, p. 83-92.

[18]     Lee J., Qiu H., Yu G., Lin J. Bearing Data Set. IMS, University of Cincinnati. NASA Ames Prognostics Data Repository, NASA Ames, Moffett Field, CA, http://ti.arc.nasa.gov/project/prognostic-data-repository.

[19]     Hong S., Wang B., Li G., Hong Q. Performance degradation assessment for bearing based on ensemble empirical mode decomposition and gaussian mixture model. Journal of Vibration and Acoustics, Vol. 136, Issue 6, 2014, p. 061006.

[20]     Doucet A., Godsill S., Andrieu C. On sequential Monte Carlo sampling methods for Bayesian filtering. Statistics and Computing, Vol. 10, Issue 3, 2000, p. 197-208.

Cite this article

Hong Sheng, Zhou Zheng, Lu Chen, Wang Baoqing, Zhao Tingdi Bearing remaining life prediction using Gaussian process regression with composite kernel functions. Journal of Vibroengineering, Vol. 17, Issue 2, 2015, p. 695‑704.


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