A novel method is proposed to exploit jointly degradation measurements originating from a set of identical systems for making a degradation prognosis. The systems experience different
degradation processes depending on operational conditions. The degradation processes are assumed to be Gamma processes. The aim is to cluster the degradation paths in classes corresponding to the different operational conditions in order to group properly the data for the estimation of degradation process parameters. A model of Gamma process mixture is considered and an expectation-minimization approach is proposed to estimate the unknown parameters. The feasibility of the method is shown on simulated cases. Prognosis results obtained with the proposed method are compared with results obtained with basic strategies (considering each system alone or all system together).
How to Cite
gamma process, clustering, data-driven prognosis
Celeux, G., & Govaert, G. (1992). A classification EM algorithm for clustering and two stochastic versions. Computational statistics & Data analysis, 14(3), 315–332.
Celeux, G., & Govaert, G. (1995). Gaussian parcimonious clustering models. Pattern Recognition, 28, 781–793.
Cinlar, E., Osman, E., & Bazant, Z. P. (1977). Stochastic process for extrapolating concrete creep. Journal of the Engineering Mechanics Division, 103(6), 1069–1088.
Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical Society ,Series B, 39(1), 1–38.
Hu, T., & Sung, S. Y. (2006). A hybrid EM approach to spatial clustering. Computational Statistics & Data Analysis, 50, 1188–1205.
Kass, R., & Raftery, A. (1995). Bayes factor. J. Am. Statistical Association, 90, 733-795.
Nystad, B. H., Gola, G., & Hulsund, J. (2012, July 3-5). Lifetime models for remaining useful life estimation with randomly distributed failure thresholds. In Proc. of first european conference of the prognostics and health management society 2012 (p. 141-147). Dresden, Germany.
Ramasso, E., & Gouriveau, R. (2014). Remaining useful life estimation by classification of predictions based on a neuro-fuzzy system and theory of belief functions. Reliability, IEEE Transactions on(99).
Saxena, A., Celaya, J., Saha, B., Saha, S., & Goebel, K. (2010). Metrics for offline evaluation of prognostics performance. International Journal of Prognostics and Health Management (IJPHM), 1(1), 20.
Shental, N., Bar-Hillel, A., Hertz, T., & Weinshall, D. (2003, August 21-24). Computing gaussian mixture models with EM using side-information. In Proc. of the 20th international conference on machine learning. Washington DC, USA.
Si, X.-S., Wang, W., Hu, C.-H., & Zhou, D.-H. (2011). Remaining useful life estimation – a review on the statistical data driven approaches. European Journal of Operational Research, 213(1), 1 - 14.
Van Noortwijk, J. (2009). A survey of the application of gamma processes in maintenance. Reliability Engineering & System Safety, 94(1), 2–21.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.