Uncertainty in Aircraft Turbofan Engine Prognostics on the C-MAPSS Dataset

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

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

Published Jun 27, 2024
Mariana Salinas-Camus Nick Eleftheroglou

Abstract

Prognostics and Health Management (PHM) plays a crucial role in maximizing operational efficiency, minimizing maintenance costs, and enhancing system  reliability. Predicting Remaining Useful Life (RUL) is a key aspect of PHM, inherently incorporating uncertainty. This paper focuses on uncertainty quantification (UQ) within Data-Driven Models (DDMs), particularly Machine Learning (ML), such as Long Short-Term Memory (LSTMs), and stochastic models namely Hidden Markov Models (HMMs). While ML models emphasize accuracy, stochastic models offer a different paradigm for prognostics, directly addressing uncertainty. Traditional categorizations of uncertainty as aleatory and epistemic face challenges in practical implementation. This paper explores how, in prognostics,  HMMs primarily tackle aleatory uncertainty, whereas LSTMs predominantly address epistemic uncertainty. It also discusses the complexities of uncertainty
management in prognostics and analyzes further an already proposed alternative approach to categorize uncertainties. Despite theoretical advancements, practical implementation remains challenging, especially for DL models due to their limited interpretability. This study sheds light on UQ challenges and offers insights for future research directions in prognostics.

How to Cite

Salinas-Camus, M., & Eleftheroglou, N. (2024). Uncertainty in Aircraft Turbofan Engine Prognostics on the C-MAPSS Dataset. PHM Society European Conference, 8(1), 10. https://doi.org/10.36001/phme.2024.v8i1.4007
Abstract 420 | PDF Downloads 219

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

Keywords

Prognostics, Uncertainty Quantification, Hidden Markov Models, Deep Learning

References
Abdar, M., Pourpanah, F., Hussain, S., Rezazadegan, D., Liu, L., Ghavamzadeh, M., . . . Acharya, U. R. (2021). A review of uncertainty quantification in deep learning: Techniques, applications and challenges. Information fusion, 76, 243–297. Caceres, J., Gonzalez, D., Zhou, T., & Droguett, E. L. (2021). A probabilistic bayesian recurrent neural network for remaining useful life prognostics considering epistemic and aleatory uncertainties. Structural Control and Health Monitoring, 28(10), e2811. Der Kiureghian, A., & Ditlevsen, O. (2009). Aleatory or epistemic? does it matter? Structural safety, 31(2), 105–112. Dong, M., & He, D. (2007a). Hidden semi-markov modelbased methodology for multi-sensor equipment health diagnosis and prognosis. European Journal of Operational Research, 178(3), 858–878. Dong, M., & He, D. (2007b). A segmental hidden semi-

markov model (hsmm)-based diagnostics and prognostics framework and methodology. Mechanical systems and signal processing, 21(5), 2248–2266. Eleftheroglou, N. (2020). Adaptive prognostics for remaining useful life of composite structures.

Eleftheroglou, N., Galanopoulos, G., & Loutas, T. (2024).

Similarity learning hidden semi-markov model for adaptive prognostics of composite structures. Reliability Engineering & System Safety, 243, 109808. Eleftheroglou, N., Mansouri, S. S., Loutas, T., Karvelis, P., Georgoulas, G., Nikolakopoulos, G., & Zarouchas, D. (2019). Intelligent data-driven prognostic methodologies for the real-time remaining useful life until the end-of-discharge estimation of the lithium-polymer batteries of unmanned aerial vehicles with uncertainty quantification. Applied Energy, 254, 113677.

Fink, O., Wang, Q., Svensen, M., Dersin, P., Lee, W.-J., & Ducoffe, M. (2020). Potential, challenges and future directions for deep learning in prognostics and health management applications. Engineering Applications of Artificial Intelligence, 92, 103678.

Folgoc, L. L., Baltatzis, V., Desai, S., Devaraj, A., Ellis, S., Manzanera, O. E. M., . . . Glocker, B. (2021). Is mc dropout bayesian? arXiv preprint arXiv:2110.04286. Fort, S., Hu, H., & Lakshminarayanan, B. (2019). Deep ensembles: A loss landscape perspective. arxiv 2019. arXiv preprint arXiv:1912.02757.

Frederick, D. K., DeCastro, J. A., & Litt, J. S. (2007). User’s guide for the commercial modular aero-propulsion system simulation (c-mapss) (Tech. Rep.).

Gal, Y., & Ghahramani, Z. (2016). Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In international conference on machine learning (pp. 1050–1059).

Giantomassi, A., Ferracuti, F., Benini, A., Ippoliti, G., Longhi, S., & Petrucci, A. (2011). Hidden markov model for health estimation and prognosis of turbofan engines. In International design engineering technical conferences and computers and information in engineering conference (Vol. 54808, pp. 681–689).

Le, T. T., Chatelain, F., & B´erenguer, C. (2014). Hidden markov models for diagnostics and prognostics of systems under multiple deterioration modes. In Proceedings of the in european safety and reliability conference-esrel (pp. 1197–1204).

Li, G., Yang, L., Lee, C.-G., Wang, X., & Rong, M. (2020). A bayesian deep learning rul framework integrating epistemic and aleatoric uncertainties. IEEE Transactions on Industrial Electronics, 68(9), 8829–8841.

Nastos, C., Komninos, P., & Zarouchas, D. (2023). Nondestructive strength prediction of composite laminates utilizing deep learning and the stochastic finite element methods. Composite Structures, 311, 116815.
Section
Technical Papers