A Framework for Bearing Prognostics in Changing Operating Conditions

Abstract:

In this paper, a framework for conducting data-driven prognostics presence of a domainshift is introduced. Domain shift is brought about by factors such as changing operations which alterthe distribution of data thus degrading the performance of learned prognostic models. The use ofWeibull-based hazard functions of the kurtosis and shape factor time domain features are exploredand affirmed as not only being trendable and monotonic but robust across operating conditions; thus,desirable for prognosis. In the learning stage, the usual procedure is to use the designated training datawhich is full lifetime data. Unfortunately, a key characteristic of test data is that its truncated whichmay offer a serious impediment to the predicting model’s performance due to it being trained with fulllifetime data only. In this research, the learning data is extended by adding its truncated versions thussignificantly improving the model’s prediction accuracy for test data. In this work, it is demonstratedthat the proposed method results in over 95% accuracy of remaining useful life prediction for bearingsoperated in different operating conditions.

• Periodical: Advanced Engineering Forum (Volume 44)
• Pages: 29-47
• DOI: https://doi.org/10.4028/www.scientific.net/AEF.44.29
• Online since: January 2022
• Authors: Esther Wangui Gituku*, James Kuria Kimotho, Jackson Githu Njiri
• Keywords: Bearings, Operating Conditions, Prognostics, Weibull Hazard Rate Distribution

References

[1] J. Qi, A. Mauricio, and K. Gryllias, Prognostics of rolling element bearings based on entropy indicators and particle filtering,, in Proceedings of the Surveillance, Vishno and AVE conferences, (2019).

[2] B. Sun, S. Zeng, R. Kang, and M. G. Pecht, Benefits and challenges of system prognostics,, IEEE Transactions on Reliability, vol. 61, pp.323-335, (2012).

DOI: 10.1109/tr.2012.2194173

[3] Y. Lei, N. Li, L. Guo, N. Li, and J. Lin, Machinery health prognostics: A systematic review from data acquisition to rul prediction,, Mechanical Systems and Signal Processing, vol. 104, pp.799-834, (2018).

DOI: 10.1016/j.ymssp.2017.11.016

[4] J. Zhu, T. Nostrand, C. Spiegel, and B. Morton, Survey of condition indicators for condition monitoring systems,, in Proceedings of the Annual Conference of the Prognostics and Health Management Society, (2014).

[5] G. Huang, H. Li, J. Ou, Y. Zhang, and M. Zhang, A reliable prognosis approach for degradation evaluation of rolling bearing using mclstm,, Sensors, vol. 20, pp.1-16, (2020).

DOI: 10.3390/s20071864

[6] B. Wu, W. Li, and M.-q. Qiu, Remaining useful life prediction of bearing with vibration signals based on a novel indicator,, Shock and Vibration, vol. 2017, pp.1-10, (2017).

DOI: 10.1155/2017/8927937

[7] B. P. Duong and J.-M. Kima, Prognosis of remaining bearing life with vibration signals using a sequential monte carlo framework,, The Journal of the Acoustical Society of America, vol. 146, pp.1-7, (2019).

DOI: 10.1121/1.5129076

[8] T. Benkedjouh, N. Zerhouni, and S. Rechak, Bearings prognostics based on blind sources separation and robust correlation analysis,, in Proceedings of the 14th International Conference on Informatics in Control, Automation and Robotics, (2017).

DOI: 10.5220/0006472006580663

[9] R. Guo and Y. Wang, Remaining useful life prognostics for the rolling bearing based on a hybrid data-driven method,, Journal of Systems and Control Engineering, vol. 235, pp.517-531, (2020).

DOI: 10.1177/0959651820948284

[10] L. Ren, Y. Sun, H. Wang, and Z. Lin, Prediction of bearing remaining useful life with deep convolution neural network,, IEEE Access, vol. 6, pp.13041-13049, (2018).

DOI: 10.1109/access.2018.2804930

[11] T. R. Kurfess, S. Billington, and S. Y. Liang, Advanced Diagnostic and Prognostic Techniques for Rolling Element Bearings.[12] N. A. S. Administration, Pcoe datasets,, 2020. data retrieved from the NASA Website, https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/.

DOI: 10.1007/1-84628-269-1_6

[13] B. P. Duoung, S. A. Khan, D. Shon, K. Im, J. Park, D.-S. Lim, B. Jang, and J.-M. Kim, A reliable health indicator for fault prognosis of bearings,, Sensors (Bassel), vol. 18, pp.3740-3756, (2018).

DOI: 10.3390/s18113740

[14] N. Li, Y. Lei, , J. Lin, and S. X. Ding, An improved exponential model for predicting remaining useful life of rolling element bearings,, IEEE Transactions on Industrial Electronics, vol. 62, pp.7762-7773, (2018).

DOI: 10.1109/tie.2015.2455055

[15] A. Wasim, S. A. Khan, and J.-M. Kim, A hybrid prognostics technique for rolling element bearings using adaptive predictive models,, IEEE Transactions on Industrial Electronics, vol. 65, pp.1577-1584, (2017).

DOI: 10.1109/tie.2017.2733487

[16] J. K. Kimotho and W. Sextro, An approach for feature extraction and selection from nontrending data for machinery prognosis,, in Proceedings of the Second European Conference of the Prognostics and Health Management Society, (2014).

[17] A. Soualhi, K. Medjaher, and N. Zerhouni, Bearing health monitoring based on hilbert-huang transform, support vector machine, and regression,, IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, vol. 465, pp.261-276, (2014).

DOI: 10.1109/tim.2014.2330494

[18] M. Boufenar, S. Rechak, and M. Rezig, Time-Frequency Analysis Techniques Review and Their Application on Roller Bearings Prognostics. (2012).

DOI: 10.1007/978-3-642-28768-8_25

[19] A. K. Mahamad, S. Saon, and T. Hiyama, Predicting remaining useful life of rotating machinery based artificial neural network,, Computers and Mathematics with Applications, vol. 60, pp.1078-1087, (2010).

DOI: 10.1016/j.camwa.2010.03.065

[20] M. Tableman and J. S. Kim, Survival Analysis Using S - Analysis of Time-to-Event Data. Chapman & Hall/CRC, (2004).

[21] D. L. Nadler and I. G. Zurbenko, Developing a weibull model extension to estimate cancer latency,, International Scholarly Research Notices Epidemiology, vol. 18, pp.1-6, (2013).

DOI: 10.5402/2013/750857

[22] M. Paterno, On random-number distributions for c++0x,, 2004. https://www.openstd.org/jtc1/sc22/wg21/docs/papers/2004/n1588.pdf.

[23] E. T. Lee and J. W. Wang, Statistical Methods for Survival Data Analysis. Wiley Interscience, (2003).

[24] G. Cybenko, Approximations by superpositions of sigmoidal functions,, Mathematics of Control, Signals, and System, vol. 2, pp.303-314, (1989).

[25] K. Hornik, Multilayer feedforward networks are universal approximators,, Neural Networks, vol. 2, pp.359-366, (1991).

DOI: 10.1016/0893-6080(89)90020-8

[26] Neural network for predictions. how to improve it," 2016. data retrieved from codeburst Website, https://www.mathworks.com/matlabcentral/answers/49959-neural-network-forpredictions-how-to-improve-it,s_tid=srchtitle.

[27] Why is my neural network performing worse as the number of hidden layers increases?," 2015. data retrieved from codeburst Website, https://www.mathworks.com/matlabcentral/answers/232036-why-is-my-neural-network-performing-worse-as-the-number-of-hidden-layersincreases?s_tid=srchtitle.[28] MathWorks ®, "Function fitting neural network," 2021. https://www.mathworks.com/help/deeplearning/ref/fitnet.html,searchHighlight=fitnet&s_tidsrchtitle.

[29] P. E. Gill and W. Murray, Algorithms for the solution of the nonlinear least-squares problem,, SIAM Journal on Numerical Analysis, vol. 15, pp.977-992, (1978).

DOI: 10.1137/0715063

[30] P. Nectoux, R. Gouriveau, K. Medjaher, E. Ramasso, B. Morello, N. Zerhouni, and C. Varnier, Pronostia: An experimental platform for bearings accelerated life test,, in Proceedings of the IEEE International Conference on Prognostics and Health Management, (2012).

[31] MathWorks ®, Monotonicity,, 2021. https://www.mathworks.com/help/predmaint/ref/monotonicity.html.

[32] MathWorks ®, Prognosability,, 2021. https://www.mathworks.com/help/predmaint/ref/prognosability.html.

[33] MathWorks ®, Trendability,, 2021. https://www.mathworks.com/help/predmaint/ref/trendability.html.

[34] MathWorks ®, How can i choose the parameters of my network?," 2013. https://www.mathworks.com/matlabcentral/answers/63601-how-can-i-choose-the-parameters-of-mynetwork,s_tid=srchtitle.

[35] IEEE PHM 2012 Challenge Details., https://github.com/Lucky-Loek/ieee-phm-2012-datachallenge-dataset. Accessed: 2021-01-30.

[36] A. Z. Hinchi and M. Tkiouat, Rolling element bearing remaining useful life estimation based on a convolutional long-short-term memory network,, PROCEDIA Computer Science, vol. 127, pp.123-132, (2018).

DOI: 10.1016/j.procs.2018.01.106

[37] D. Zhao and F. Liu, Cross-condition and cross-platform remaining useful life estimation via adversarial-based domain adaptation,, 2021. https://www.researchsquare.com/article/rs669444/v1.

DOI: 10.21203/rs.3.rs-669444/v1

[38] M. Wentao, B. Sun, and L. Wang, A new deep dual temporal domain adaptation method for online detection of bearings early fault,, Entropy, vol. 23(2):162, pp.1-19, (2021).

DOI: 10.3390/e23020162

[39] P. R. d. Oliveira da Costa, A. Akcay, and U. Kayma, Remaining useful lifetime prediction via deep domain adaptation,, Reliability Engineering & System Safety, vol. 195, pp.1-30, (2020).

DOI: 10.1016/j.ress.2019.106682

[40] J. Li, X. Li, and D. He, Domain adaptation remaining useful life prediction method based on adabn-dcnn,, in Proceedings of the Annual Conference of the PHM Society, (2019).

DOI: 10.1109/phm-qingdao46334.2019.8942857

[41] M. Ragab, C. S. Foo, C. K. Kwoh, R. Yan, and X. Li, Contrastive adversarial domain adaptation for machine remaining useful life prediction,, IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, vol. 17, pp.5239-5249, (2021).

DOI: 10.1109/tii.2020.3032690

[42] M. Russell and P. Wang, Domain adversarial transfer learning for generalized tool wear prediction,, in Proceedings of the Annual Conference of the PHM Society, (2020).

DOI: 10.36001/phmconf.2020.v12i1.1137