Bridging Methods and Data in System-Level Prognostics: A Comprehensive Review
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
System-level prognostics (SLP) is a core problem in prognostics and health management (PHM) that seeks to predict future health states or remaining useful life (RUL) in complex multi-component systems where degradations interact through functional and operational interdependencies.
Despite significant progress, the SLP literature remains fragmented, and existing reviews largely offer taxonomies without systematically linking modeling assumptions, data availability, and validation choices to reported performance and reproducibility.
This paper offers a data‑centric synthesis of the SLP landscape by integrating insights from influential reviews, technical contributions, and publicly available prognostics datasets.
We conduct an analysis to characterize publication trends and research domains, identify and quantify the coverage of recurring SLP challenges, and assess how current methodologies address (or overlook) these issues.
We also curate a dataset catalog to quantify gaps between methodological ambitions and benchmarking resources.
The study concludes by outlining priority directions for advancing reproducibility, data diversity, and deployment‑oriented SLP research.
How to Cite
##plugins.themes.bootstrap3.article.details##
Prognostics and Health Management, system-level prognostics, remaining useful life, component interdependencies, mission profile, multi-component systems
Alaswad, S., & Xiang, Y. (2017, January). A review on condition-based maintenance optimization models for stochastically deteriorating system. Reliability Engineering & System Safety, 157, 54–63. doi: 10.1016/j.ress.2016.08.009
Cao, X., Peng, K., & Jiao, R. (2024, September). Degradation modeling and remaining life prediction for a multi-component system under triple uncertainties. Computers & Industrial Engineering, 195, 110432. doi: 10.1016/j.cie.2024.110432
Chiachío, J., Chiachío, M., Prescott, D., & Andrews, J. (2019, January). A knowledge-based prognostics framework for railway track geometry degradation. Reliability Engineering & System Safety, 181, 127–141. doi: 10.1016/j.ress.2018.07.004
Cubillo, A., Perinpanayagam, S., & Esperon-Miguez, M. (2016, August). A review of physics-based models in prognostics: Application to gears and bearings of rotating machinery. Advances in Mechanical Engineering, 8(8), 1687814016664660. doi: 10.1177/1687814016664660
Deng, W., Nguyen, K. T. P., Medjaher, K., Gogu, C., & Morio, J. (2023, December). Physics-informed machine learning in prognostics and health management: State of the art and challenges. Applied Mathematical Modelling, 124, 325–352. doi: 10.1016/j.apm.2023.07.011
Dobs, T., Elsotohy, M., Jaeschke, J., Sehr, F., Strogies, J., & Wilke, K. (2022, November). Multi-domain system level modeling approach for assessment of degradation behaviour under thermal and thermo-mechanical stress. Microelectronics Reliability, 138, 114710. doi: 10.1016/j.microrel.2022.114710
Huang, K., Jia, G., Jiao, Z., Wang, Q., Huang, F., & Cai, Y. (2025, November). Remaining Useful Life Prediction Through Adaptive Spatiotemporal Graph Neural Network Based on Relationship Mining for Complex Aviation Equipment. IEEE Sensors Journal, 25(21), 40775–40792. doi: 10.1109/JSEN.2025.3605144
Jose, S., Nguyen, K. T. P., & Medjaher, K. (2026, January). Enhancing industrial prognostic accuracy in noisy and missing data context: Assessing multimodal learning performance. Journal of Intelligent Manufacturing, 37(1), 373–397. doi: 10.1007/s10845-024-02544-7
Jose, S., Nguyen, K. T. P., Medjaher, K., Zemouri, R., Lévesque, M., & Tahan, A. (2024, December). Advancing multimodal diagnostics: Integrating industrial textual data and domain knowledge with large language models. Expert Systems with Applications, 255, 124603. doi: 10.1016/j.eswa.2024.124603
Jose, S., Zemouri, R., Nguyen, K. T. P., Medjaher, K., Lévesque, M., & Tahan, A. (2025, May). Prognostics of complex machinery with sparse multilabel multimodal run-to-failure data: A graph neural network approach. Advanced Engineering Informatics, 65, 103361. doi: 10.1016/j.aei.2025.103361
Kang, W., Zhang, X., Zhang, J., Chen, X., Huang, H., He, B., ... Zhu, H. (2025, June). Multimodal data generative fusion method for complex system health condition estimation. Scientific Reports, 15(1), 20026. doi: 10.1038/s41598-025-04985-3
Kim, S., Choi, J.-H., & Kim, N. H. (2021, November). Challenges and Opportunities of System-Level Prognostics. Sensors (Basel, Switzerland), 21(22), 7655. doi: 10.3390/s21227655
Liu, C., Sun, J., Liu, H., Lei, S., & Hu, X. (2020, September). Complex engineered system health indexes extraction using low frequency raw time-series data based on deep learning methods. Measurement, 161, 107890. doi: 10.1016/j.measurement.2020.107890
Lu, Y., Wang, S., Zhang, C., Chen, R., Dui, H., & Wang, Y. (2026, January). Industrial IoT-driven condition-based maintenance plus for complex system with multiple dependencies. Advanced Engineering Informatics, 69, 103939. doi: 10.1016/j.aei.2025.103939
Lycksam, A., O’Nils, M., & Qureshi, F. Z. (2025). A Prognostic Framework for Rotating Machines Considering Multi-Component Fault Scenarios. IEEE Access, 13, 91682–91692. doi: 10.1109/ACCESS.2025.3572582
Nguyen, K. T. P., Medjaher, K., & Tran, D. T. (2022, September). A review of artificial intelligence methods for engineering prognostics and health management with implementation guidelines. Artif. Intell. Rev., 56(4), 3659–3709. doi: 10.1007/s10462-022-10260-y
Sai, V. C., Shcherbakov, M. V., & Tran, V. P. (2019). Data-Driven Framework for Predictive Maintenance in Industry 4.0 Concept. In A. G. Kravets, P. P. Groumpos, M. Shcherbakov, & M. Kultsova (Eds.), Creativity in Intelligent Technologies and Data Science (pp. 344–358). Cham: Springer International Publishing. doi: 10.1007/978-3-030-29743-5_28
Shi, H., & Zeng, J. (2016, March). Real-time prediction of remaining useful life and preventive opportunistic maintenance strategy for multi-component systems considering stochastic dependence. Computers & Industrial Engineering, 93, 192–204. doi: 10.1016/j.cie.2015.12.016
Skordilis, E., & Moghaddass, R. (2020, January). A Double Hybrid State-Space Model for Real-Time Sensor-Driven Monitoring of Deteriorating Systems. IEEE Transactions on Automation Science and Engineering, 17(1), 72–87. doi: 10.1109/TASE.2019.2921285
Solís-Martín, D., Galán-Páez, J., & Borrego-Díaz, J. (2025, February). PHMD: An easy data access tool for prognosis and health management datasets. SoftwareX, 29, 102039. doi: 10.1016/j.softx.2025.102039
Tamssaouet, F., Nguyen, K. T., Medjaher, K., & Orchard, M. E. (2023, June). System-level failure prognostics: Literature review and main challenges. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 237(3), 524–545. doi: 10.1177/1748006X221118448
Tamssaouet, F., Nguyen, K. T. P., & Medjaher, K. (2021, August). System-Level Prognostics Under Mission Profile Effects Using Inoperability Input–Output Model. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 51(8), 4659–4669. doi: 10.1109/TSMC.2019.2944834
Tamssaouet, F., Nguyen, K. T. P., Medjaher, K., & Orchard, M. E. (2021, June). Degradation Modeling and Uncertainty Quantification for System-Level Prognostics. IEEE Systems Journal, 15(2), 1628–1639. doi: 10.1109/JSYST.2020.2983376
Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., & Abbeel, P. (2017, September). Domain randomization for transferring deep neural networks from simulation to the real world. In 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 23–30). doi: 10.1109/IROS.2017.8202133
Van Horenbeek, A., & Pintelon, L. (2013, December). A dynamic predictive maintenance policy for complex multi-component systems. Reliability Engineering & System Safety, 120, 39–50. doi: 10.1016/j.ress.2013.02.029
Wang, X., Si, X., Xi, X., & Zhou, D. (2025). Adaptive Remaining Useful Life Prediction Based on a System-Level Variable Structure Degradation Model. IEEE Transactions on Instrumentation and Measurement, 74, 1–13. doi: 10.1109/TIM.2025.3573776
Xiao, C., & Zheng, P. (2023, October). Integrated system-level prognosis for hybrid systems subjected to multiple intermittent faults. Reliability Engineering & System Safety, 238, 109401. doi: 10.1016/j.ress.2023.109401
Zhang, X., Leng, Z., Zhao, Z., Li, M., Yu, D., & Chen, X. (2023, August). Spatial-temporal dual-channel adaptive graph convolutional network for remaining useful life prediction with multi-sensor information fusion. Advanced Engineering Informatics, 57, 102120. doi: 10.1016/j.aei.2023.102120
Zhang, Y., Zhang, C., Wang, S., Dui, H., & Chen, R. (2024, January). Health indicators for remaining useful life prediction of complex systems based on long short-term memory network and improved particle filter. Reliability Engineering & System Safety, 241, 109666. doi: 10.1016/j.ress.2023.109666
Zhou, J., Tang, D., Yu, J., Song, Y., Li, X., & Liu, H. (2024). Construction of Interpretable Health Indicators for System-Level Fault Prognosis Driven by Inductive Generative Learning. IEEE Transactions on Instrumentation and Measurement, 73, 1–12. doi: 10.1109/TIM.2024.3458064
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
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.