Data-Driven Remaining Useful Life Estimation Inference-Based Versus Direct Prediction

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Nov 5, 2024
Ark Ifeanyi Mattia Zanotelli Jamie Coble

Abstract

This paper explores the development and application of data-driven prognostic models for estimating the Remaining Useful Life (RUL) of Nuclear Power Plant (NPP) condensers experiencing tube fouling. Due to the unavailability of run-to-failure industry sensor data, we utilized simulated data generated by the Asherah Nuclear Power Plant Simulator (ANS), initially designed by the International Atomic Energy Agency (IAEA) and programmed in Simulink for cyber security simulations. ANS's adaptability allows it to simulate Pressurized Water Reactor (PWR) behaviors given a time series of operating conditions and to introduce degradation modules to mimic fouling effects. Our study compares two primary approaches applied to data generated by ANS: inference-based and direct prediction methods. The selected inference-based approach estimates the health state of the condenser using a pipeline formed by an Auto Associative Kernel Regressor and a Hidden Markov Model (HMM), which subsequently combines the state estimates with its parameters to predict the RUL. The direct prediction method employs a Gradient Boosting Regressor Decision Tree (GBRDT) to map input variables directly to RUL. Our findings demonstrate the efficacy and limitations of each method through the case study, providing valuable insights for the adoption of data-driven RUL estimation techniques in industrial and energy applications.

How to Cite

Ifeanyi, A., Zanotelli, M., & Coble, J. (2024). Data-Driven Remaining Useful Life Estimation: Inference-Based Versus Direct Prediction. Annual Conference of the PHM Society, 16(1). https://doi.org/10.36001/phmconf.2024.v16i1.4071
Abstract 114 | PDF Downloads 122

##plugins.themes.bootstrap3.article.details##

Keywords

Condition-based Maintenance, Hidden Markov Models, Prognostics, Asset Health Management, Gradient Boosting Regression Tree

References
An, D., Choi, J. H., & Kim, N. H. (2013). Options for prognostics methods: A review of data-driven and physicsbased prognostics. In 54th aiaa/asme/asce/ahs/asc structures, structural dynamics, and materials conference (p. 1940).

Busquim e Silva, R., Piqueira, J., Cruz, J., & Marques, R. (2021). Cybersecurity assessment framework for digital interface between safety and security at nuclear power plants. International Journal of Critical Infrastructure Protection, 34, 100453. doi: https://doi.org/10.1016/j.ijcip.2021.100453

Chen, Z., Li, Y., Xia, T., & Pan, E. (2019). Hidden Markov model with auto-correlated observations for remaining useful life prediction and optimal maintenance policy. Reliability Engineering and System Safety, 184(C), 123-136. doi: 10.1016/j.ress.2017.09.00

Coble, J., & Hines, J. (2009, 01). Fusing data sources for optimal prognostic parameter selection. Transactions of the American Nuclear Society, 100, 211-212.

Coble, J., & Hines, J. (2011, 01). Applying the general path model to estimation of remaining useful life. International Journal of Prognostics and Health Management, 2, 2153-2648. doi: 10.36001/ijphm.2011.v2i1.1352

Cubillo, A., Perinpanayagam, S., & Esperon-Miguez, M. (2016). A review of physics-based models in prognostics: Application to gears and bearings of rotating machinery. Advances in Mechanical Engineering, 8(8), 1687814016664660.

Cui, L., Li, W., Wang, X., Zhao, D., & Wang, H. (2022). Comprehensive remaining useful life prediction for rolling element bearings based on timevarying particle filtering. IEEE Transactions on Instrumentation and Measurement, 71, 1-10. doi: 10.1109/TIM.2022.3163167

Dong, M., & He, D. (2007). A segmental hidden semimarkov model (hsmm)-based diagnostics and prognostics framework and methodology. Mechanical Systems and Signal Processing, 21(5), 2248-2266. doi: https://doi.org/10.1016/j.ymssp.2006.10.001

Elattar, H. M., Elminir, H. K., & Riad, A. (2016). Prognostics: a literature review. Complex&Intelligent Systems, 2(2), 125–154.

Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, 1189– 1232.

Friedman, J. H., & Meulman, J. J. (2003). Multiple additive regression trees with application in epidemiology. Statistics in medicine, 22(9), 1365–1381.

Huang, Y., Liu, Y., Li, C., &Wang, C. (2019). Gbrtvis: online analysis of gradient boosting regression tree. Journal of Visualization, 22, 125–140.
Ibrahim, S. M., & Attia, S. I. (2015). The influence of condenser cooling seawater fouling on the thermal performance of a nuclear power plant.

Annals of Nuclear Energy, 76, 421-430. doi: https://doi.org/10.1016/j.anucene.2014.10.018 Ifeanyi, A. (2024). A graph neural network approach to system-level health index and remaining useful life estimation. In 16th annual conference of the prognostics and health management society (phmconf).

Ifeanyi, A. O., Coble, J. B., & Saxena, A. (2024). A deep learning approach to within-bank fault detection and diagnostics of fine motion control rod drives. International Journal of Prognostics and Health Management, 15(1).

Khelif, R., Chebel-Morello, B., Malinowski, S., Laajili, E., Fnaiech, F., & Zerhouni, N. (2016). Direct remaining useful life estimation based on support vector regression. IEEE Transactions on industrial electronics, 64(3), 2276–2285.

Kundu, P., Darpe, A. K., & Kulkarni, M. S. (2020). An ensemble decision tree methodology for remaining useful life prediction of spur gears under natural pitting progression. Structural Health Monitoring, 19(3), 854– 872.

Ma, Y., Yao, M., Liu, H., & Tang, Z. (2022). State of health estimation and remaining useful life prediction for lithium-ion batteries by improved particle swarm optimization-back propagation neural network. Journal of Energy Storage, 52, 104750.

Martins, A., Fonseca, I., Farinha, J. T., Reis, J., & Cardoso, A. J. M. (2021). Maintenance prediction through sensing using hidden markov models—a case study. Applied Sciences, 11(16).

Patil, S., Patil, A., Handikherkar, V., Desai, S., Phalle, V. M., & Kazi, F. S. (2018). Remaining useful life (rul) prediction of rolling element bearing using random forest and gradient boosting technique. In Asme international mechanical engineering congress and exposition (Vol. 52187, p. V013T05A019).

Peng, W., Ye, Z.-S., & Chen, N. (2019). Bayesian deep learning- based health prognostics toward prognostics uncertainty. IEEE Transactions on Industrial Electronics, 67(3), 2283–2293.

Prettenhofer, P., & Louppe, G. (2014). Gradient boosted regression trees in scikit-learn. In Pydata 2014.

Rabiner, L. (1989). A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257-286. doi: 10.1109/5.18626

Rezki, N., & Rezgui,W. (2024). Enhancing turbofan engines reliability through comparative analysis of svr and lsboost for remaining useful life estimation. In 2024 2nd international conference on electrical engineering and automatic control (iceeac) (pp. 1–4).

Sankavaram, C., Kodali, A., Pattipati, K., Singh, S., Zhang, Y., & Salman, M. (2016). An inference-based prognostic framework for health management of automotive systems. International Journal of Prognostics and Health Management, 7(2).

Saxena, A., Celaya, J., Balaban, E., Goebel, K., Saha, B., Saha, S., & Schwabacher, M. (2008). Metrics for evaluating performance of prognostic techniques. In 2008 international conference on prognostics and health management (pp. 1–17).

Saxena, A., Goebel, K., Simon, D., & Eklund, N. (2008). Damage propagation modeling for aircraft engine runto- failure simulation. In 2008 international conference on prognostics and health management (pp. 1–9).

Song, K., & Cui, L. (2022). A common random effect induced bivariate gamma degradation process with application to remaining useful life prediction. Reliability Engineering & System Safety, 219, 108200. doi: https://doi.org/10.1016/j.ress.2021.108200

Song, L., Gui, X., Du, J., Fan, Z., Li, M., & Guo, L. (2024). A novel transfer learning approach for state-of-health prediction of lithium-ion batteries in the absence of run to failure data. IEEE Transactions on Instrumentation and Measurement.

Song, Y., Li, L., Peng, Y., & Liu, D. (2018). Lithium-ion battery remaining useful life prediction based on grurnn. In 2018 12th international conference on reliability, maintainability, and safety (icrms) (pp. 317–322).

Sundar, S., Rajagopal, M. C., Zhao, H., Kuntumalla, G., Meng, Y., Chang, H. C., . . . Salapaka, S. (2020). Fouling modeling and prediction approach for heat exchangers using deep learning. International Journal of Heat and Mass Transfer, 159, 120112. doi: https://doi.org/10.1016/j.ijheatmasstransfer.2020.120112

Sa, A., Andrade, A., Soares, A., Naves, E., & Nasuto, S. (2021, 01). On the initialization of parameters of hidden markov models.. doi: 10.37423/210203594

Tobon-Mejia, D. A., Medjaher, K., Zerhouni, N., & Tripot, G. (2010). A mixture of gaussians hidden markov model for failure diagnostic and prognostic. In 2010 ieee international conference on automation science and engineering (p. 338-343). doi: 10.1109/COASE.2010.5584759

Valladares, H., Li, T., Zhu, L., El-Mounayri, H., Hashem, A. M., Abdel-Ghany, A. E., & Tovar, A. (2022). Gaussian process-based prognostics of lithium-ion batteries and design optimization of cathode active materials. Journal of Power Sources, 528, 231026. doi: https://doi.org/10.1016/j.jpowsour.2022.231026

Wald, A., & Wolfowitz, J. (1948). Optimum character of the sequential probability ratio test. The Annals of Mathematical Statistics, 326–339.

Wang, H., Ma, X., & Zhao, Y. (2019). An improved wiener process model with adaptive drift and diffusion for online remaining useful life prediction. Mechanical Systems and Signal Processing, 127, 370-387. doi: https://doi.org/10.1016/j.ymssp.2019.03.019

Wen, Y., Rahman, M. F., Xu, H., & Tseng, T.-L. B. (2022). Recent advances and trends of predictive maintenance from data-driven machine prognostics perspective. Measurement, 187, 110276.

Xiao, H., Hines, A., Zhang, F., Coble, J. B., & Hines, J. W. (2023). Prognostics and health management for maintenance-dependent processes. Nuclear Technology, 209(3), 419–436.

Xu, X., Li, X., Ming, W., & Chen, M. (2022). A novel multi-scale cnn and attention mechanism method with multi-sensor signal for remaining useful life prediction. Computers & Industrial Engineering, 169, 108204.

Yang, F., Wang, D., Xu, F., Huang, Z., & Tsui, K.-L. (2020). Lifespan prediction of lithium-ion batteries based on various extracted features and gradient boosting regression tree model. Journal of Power Sources, 476, 228654.

Yu, J. (2015). Machine health prognostics using the Bayesian inference- based probabilistic indication and high-order particle filtering framework. Journal of Sound and Vibration, 358, 97–110.

Zanotelli, M., Hines, J. W., & Coble, J. B. (2024). Combining similarity measures and left-right hidden markov models for prognostics of items subjected to perfect and imperfect maintenance. Nuclear Science and Engineering, 1–15.

Zemel, R., & Pitassi, T. (2000). A gradient-based boosting algorithm for regression problems. Advances in neural information processing systems, 13.

Zhang, Y., Xiong, R., He, H., & Liu, Z. (2017). A lstmrnn method for the lithuim-ion battery remaining useful life prediction. In 2017 prognostics and system health management conference (phm-harbin) (pp. 1–4).

Zhang, Y., Yang, T., Zhou, H., Lyu, D., Zheng, W., & Li, X. (2023). A prognosis method for condenser fouling based on differential modeling. Energies, 16(16).

Zhao, W., Shi, T., & Wang, L. (2020). Fault diagnosis and prognosis of bearing based on hidden markov model with multi-features. Applied Mathematics and Nonlinear Sciences, 5(1), 71–84.

Zhu, R., Chen, Y., Peng, W., & Ye, Z.-S. (2022). Bayesian deep-learning for rul prediction: An active learning perspective. Reliability Engineering & System Safety, 228, 108758.
Section
Technical Research Papers

Most read articles by the same author(s)