Unsupervised Kernel Regression Modeling Approach for RUL Prediction



Published Jul 8, 2014
Racha Khelif Simon Malinowski Brigitte Chebel - Morello Noureddine Zerhouni


Recently, Prognostics and Health Management (PHM) has gained attention from the industrial world since it aims at increasing safety and reliability while reducing the maintenance cost by providing a useful prediction about the Remaining Useful Life (RUL) of critical components/system. In this paper, an Instance-Based Learning (IBL) approach is proposed for RUL prediction. Instances correspond to trajectories representing run-to-failure data of a component. These trajectories are modeled using Unsupervised Kernel Regression (UKR). A historical database is used to learn a UKR model for each training unit. These models fuse the run-tofailure data into a single feature that evolves over time and hence allow the construction of a library of instances. When
unseen sensory data arrive, the learned UKR models are used to construct the test degradation trajectories. RUL is deduced by comparing the test degradation trajectory to the library of instance. Only the most similar train instances are kept for RUL prediction. The proposed approach was tested and compared to approaches that apply linear regression and PCA to model the library of instances. Results highlight the benefit of using UK compared to other approaches.

How to Cite

Khelif, R., Malinowski, S., Chebel - Morello, B. ., & Zerhouni, N. (2014). Unsupervised Kernel Regression Modeling Approach for RUL Prediction. PHM Society European Conference, 2(1). https://doi.org/10.36001/phme.2014.v2i1.1522
Abstract 542 | PDF Downloads 109




Goebel, K., & Bonissone, P. (2005). Prognostic information fusion for constant load systems. In Information fusion, 2005 8th international conference on (Vol. 2, pp. 9–pp).
ISO. (2004). Condition monitoring and diagnostics of machines, prognostics part 1: General guidelines (Vol. ISO/IEC Directives Part 2; Tech. Rep. No. ISO13381-1). International Organization for Standardization.
Meinicke, P., Klanke, S., Memisevic, R., & Ritter, H. (2005). Principal surfaces from unsupervised kernel regression. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 27(9), 1379–1391.
Memisevic, R. (2003). Unsupervised kernel regression for nonlinear dimensionality reduction. Unpublished doctoral dissertation, University of Bielefeld.
Mosallam, A., Medjaher, K., & Zerhouni, N. (2013). Bayesian approach for remaining useful life prediction. Chemical Engineering Transactions, 33, 139–144.
Ramasso, E., Rombaut, M., & Zerhouni, N. (2013). Joint prediction of continuous and discrete states in time-series based on belief functions. Cybernetics, IEEE Transactions on, 43(1), 37–50.
Saxena, A., Goebel, K., Simon, D., & Eklund, N. (2008). Damage propagation modeling for aircraft engine runto-failure simulation. In Prognostics and health management, 2008. phm 2008. international conference on (pp. 1–9).
Wang, T., Yu, J., Siegel, D., & Lee, J. (2008). A similaritybased prognostics approach for remaining useful life estimation of engineered systems. In Prognostics and health management, 2008. phm 2008. international conference on (pp. 1–6).
Xue, F., Bonissone, P., Varma, A., Yan, W., Eklund, N., & Goebel, K. (2008). An instance-based method for remaining useful life estimation for aircraft engines. Journal of Failure Analysis and Prevention, 8(2), 199–206.
Zio, E., Di Maio, F., & Stasi, M. (2010). A data-driven approach for predicting failure scenarios in nuclear systems. Annals of Nuclear Energy, 37(4), 482–491.
Technical Papers

Similar Articles

<< < 1 2 3 4 5 6 7 8 9 10 > >> 

You may also start an advanced similarity search for this article.