Machine learning-driven predictive maintenance models for hydrogen fuel cell systems in smart transportation networks

Authors

Article ID: 636
101 Views

DOI:

https://doi.org/10.18686/cest636

Keywords:

predictive maintenance; hydrogen fuel cell systems; smart transportation networks; proton exchange membrane fuel cell; remaining useful life; machine learning; hybrid deep learning

Abstract

Hydrogen Fuel Cells (HFCs) are a central technology for advancing decarbonized mobility in Smart Transportation Networks (STN), yet their durability is limited by advanced electrochemical and thermal degradation. Anticipating such errors requires Predictive Maintenance Models (PMM) capable of extracting health indicators and predicting model behavior under dynamic operating conditions. This study develops Machine Learning (ML)-driven models for Fault Detection (FD), Remaining Useful Life (RUL) prediction, and prognostic reliability test in the Proton Exchange Membrane Fuel Cell (PEMFC) model. A 24-cell PEMFC stack dataset comprising 1500 h of operation under automotive load cycling was employed to analyze Supervised Learning (SL), Deep Temporal Networks (DTN), and a physics-guided hybrid residual model. Model training used cross-entropy and Mean Squared Error (MSE) objectives with causality-preserving temporal partitioning. Results proved that Deep Learning (DL) methods outperformed traditional classifiers, with the hybrid residual LSTM achieving 97.3% classification accuracy, 65.1 h RUL prediction RMSE, and early prognostic stabilization 85 h before error. Robustness analyses verified resilience against sensor noise, and computational profiling confirmed real-time feasibility with implication latency below 50 ms. These results establish that integrating physics-guided constraints into data-driven models yields accurate, deployable predictive maintenance for HFC, thereby enhancing safety, efficiency, and availability in STN.

Downloads

Published

2026-02-24

How to Cite

M. Ali, H., Tripathi, K., Marapelli, B., Smerat, A., Tayseer Ayasrah, F., Dhas, G. J. J. C. M., Madaminov, B., & Sengan, S. (2026). Machine learning-driven predictive maintenance models for hydrogen fuel cell systems in smart transportation networks. Clean Energy Science and Technology, 4(1). https://doi.org/10.18686/cest636

Issue

Vol. 4 No. 1 (2026)

Section

Article

License

Copyright (c) 2026 Hayder M. Ali, Khushboo Tripathi, Bhaskar Marapelli, Aseel Smerat, Firas Tayseer Ayasrah, Gnana Jeslin Jeya Chandir Mohana Dhas, Bekzod Madaminov, Sudhakar Sengan

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

References

1. Kiani M, Zhao Y, Zhang R. Proton exchange membrane fuel cells: recent developments and future perspectives. Chemical Communications. 2025; 61(52): 9392–9411. doi: 10.1039/D5CC01478F DOI: https://doi.org/10.1039/D5CC01478F

2. Osman AI, Chen Z, Elgarahy AM, et al. Membrane Technology for Energy Saving: Principles, Techniques, Applications, Challenges, and Prospects. Advanced Energy and Sustainability Research. 2024; 5(5): 2400011. doi: 10.1002/aesr.202400011 DOI: https://doi.org/10.1002/aesr.202400011

3. Arun M, Giddey S, Joseph P, et al. Challenges and mitigation strategies for general failure and degradation in polymer electrolyte membrane-based fuel cells and electrolysers. Journal of Materials Chemistry A. 2025; 13(16): 11236–11263. doi: 10.1039/D4TA08823A DOI: https://doi.org/10.1039/D4TA08823A

4. Kumar P, Ganguly S. Prognostic Modeling for PEM Fuel Cells: A Comparative Analysis Among Different Types of Approaches. IEEE Access. 2025; 13: 156768–156784. doi: 10.1109/ACCESS.2025.3606630 DOI: https://doi.org/10.1109/ACCESS.2025.3606630

5. Xu Y, Li X, Cao Y, et al. Review: application of machine learning methods to performance evaluation, lifetime prediction and integrated management of hydrogen fuel cells. Environment, Development and Sustainability. 2025. doi: 10.1007/s10668-025-06386-y DOI: https://doi.org/10.1007/s10668-025-06386-y

6. Algburi RNA, Aljibori HSS, Al-Huda Z, et al. Advanced fault diagnosis in industrial robots through hierarchical hyper-laplacian priors and singular spectrum analysis. Complex & Intelligent Systems. 2025; 11(6): 282. doi: 10.1007/s40747-025-01915-8 DOI: https://doi.org/10.1007/s40747-025-01915-8

7. Almngoshi HZ, C M, Kanaka Ratnam AS, et al. Data Visualisation Models for Analytics Use Artificial Intelligence to Predict Diabetes in Women. Journal of Machine and Computing. 2025; 5(1): 551–560. doi: 10.53759/7669/jmc202505043 DOI: https://doi.org/10.53759/7669/jmc202505043

8. Abdul Raheem AK, Zuhair M. Enhancing credit risk management in the banking sector through machine learning-based predictive models. Journal of Theoretical and Applied Information Technology. 2023; 101(16): 6522–6530. Available online: https://www.researchgate.net/publication/373923311_enhancing_credit_risk_management_in_the_banking_sector_through_machine_learning-based_predictive_models

9. Algburi RNA, Aljibori HSS, Al-Huda Z, et al. SSA-Sparse MHD: Singular Spectrum Analysis Paired with Sparse Maximum Harmonics Deconvolution for Detecting Feeble Defect Signals in Industrial Robots. In: Proceedings of the 2024 8th International Artificial Intelligence and Data Processing Symposium (IDAP); 21 September 2024; Malatya, Türkiye. pp. 1–9. doi: 10.1109/IDAP64064.2024.10710846 DOI: https://doi.org/10.1109/IDAP64064.2024.10710846

10. Algburi RNA, Sultan Aljibori HS, Al-Huda Z, et al. HHLP-SSA: Enhanced Fault Diagnosis in Industrial Robots Using Hierarchical Hyper-Laplacian Prior and Singular Spectrum Analysis. In: Proceedings of the 2024 8th International Artificial Intelligence and Data Processing Symposium (IDAP); 21 September 2024; Malatya, Türkiye. pp. 1–8. doi: 10.1109/IDAP64064.2024.10711014 DOI: https://doi.org/10.1109/IDAP64064.2024.10711014

11. Wu H, Zhang R, Zhu W, et al. A health index-based approach for fuel cell lifetime estimation. iScience. 2024; 27(11): 110979. doi: 10.1016/j.isci.2024.110979 DOI: https://doi.org/10.1016/j.isci.2024.110979

12. Chen L, Yang J, Deng P, et al. Remaining useful life prediction of fuel cells using a dual data-driven model with relative power loss rate-based health indicator under real-world traffic conditions. International Journal of Hydrogen Energy. 2025; 157: 150366. doi: 10.1016/j.ijhydene.2025.150366 DOI: https://doi.org/10.1016/j.ijhydene.2025.150366

13. Gürsoy Mİ. Short and long-term prognostics of the remaining useful life of a proton exchange membrane fuel cell using deep learning and transformer model. International Journal of Hydrogen Energy. 2025; 143: 1120–1132. doi: 10.1016/j.ijhydene.2024.12.512 DOI: https://doi.org/10.1016/j.ijhydene.2024.12.512

14. Huang B, Wang J. Applications of Physics-Informed Neural Networks in Power Systems —A Review. IEEE Transactions on Power Systems. 2023; 38(1): 572–588. doi: 10.1109/TPWRS.2022.3162473 DOI: https://doi.org/10.1109/TPWRS.2022.3162473

15. Wang F, Zhai Z, Zhao Z, et al. Physics-informed neural network for lithium-ion battery degradation stable modeling and prognosis. Nature Communications. 2024; 15(1): 4332. doi: 10.1038/s41467-024-48779-z DOI: https://doi.org/10.1038/s41467-024-48779-z

16. Zerrougui I, Li Z, Hissel D. Physics-Informed Neural Network for modeling and predicting temperature fluctuations in proton exchange membrane electrolysis. Energy and AI. 2025; 20: 100474. doi: 10.1016/j.egyai.2025.100474 DOI: https://doi.org/10.1016/j.egyai.2025.100474

17. Ko T, Kim D, Park J, et al. Physics-informed neural network for long-term prognostics of proton exchange membrane fuel cells. Applied Energy. 2025; 382: 125318. doi: 10.1016/j.apenergy.2025.125318 DOI: https://doi.org/10.1016/j.apenergy.2025.125318

18. Pettorossi C, Morvillier R, Heiries V, et al. Physics-guided fault diagnosis method for proton exchange membrane fuel cells based on LSTM neural network. Journal of Power Sources. 2025; 626: 235696. doi: 10.1016/j.jpowsour.2024.235696 DOI: https://doi.org/10.1016/j.jpowsour.2024.235696

19. Zhou N, Zeng H, Zheng Z, et al. PEMFC RUL Prediction for Non-Stationary Time Series Based on Crossformer Model. Applied Sciences. 2025; 15(5): 2515. doi: 10.3390/app15052515 DOI: https://doi.org/10.3390/app15052515

20. Bhattarai S, Mohammed MKA, Madan J, et al. Comparative Study of Different Perovskite Active Layers for Attaining Higher Efficiency Solar Cells: Numerical Simulation Approach. Sustainability (Switzerland). 2023; 15(17): 12805. doi: 10.3390/su151712805 DOI: https://doi.org/10.3390/su151712805

21. Ahn J, Lee Y, Kim N, et al. Federated Learning for Predictive Maintenance and Anomaly Detection Using Time Series Data Distribution Shifts in Manufacturing Processes. Sensors. 2023; 23(17): 7331. doi: 10.3390/s23177331 DOI: https://doi.org/10.3390/s23177331

22. Hosni H. Secure Predictive Maintenance for Industrial Systems Using Federated Learning. Journal of Innovations in Business and Industry. 2025; 4(1): 69–78. doi: 10.61552/JIBI.2026.01.007 DOI: https://doi.org/10.61552/JIBI.2026.01.007

23. Mohammed MN, Aljibori HSS, Al-Tamimi A, et al. Toward Sustainable Smart Cities in Bahrain: A Groundbreaking Approach to Marine Renewable Energy Harnessing Sea Tides and Waves for a Greener Energy Future. In: Proceedings of the IEEE 8th International Conference on Engineering Technologies and Applied Sciences; 25–27 October 2023; Manama, Bahrain. doi: 10.1109/ICETAS59148.2023.10346346 DOI: https://doi.org/10.1109/ICETAS59148.2023.10346346

24. Saadh, MJ, Ali ABM, Hanoon Z, et al. The ability of ZnO and MgO nanocages for adsorption and sensing performance of anticancer drug detection. Journal of Molecular Graphics and Modelling. 2025; 137: 109003. doi: 10.1016/j.jmgm.2025.109003 DOI: https://doi.org/10.1016/j.jmgm.2025.109003

25. Danielis R, Scorrano M, Masutti M, et al. Fuel Cell Electric Buses: A Systematic Literature Review. Energies. 2024; 17(20): 5096. doi: 10.3390/en17205096 DOI: https://doi.org/10.3390/en17205096

26. Siegel JB, Stefanopoulou AG, McKahn D. 24 Cell Proton Exchange Membrane Fuel Cell Stack, 300 Square cm Area Voltage Parameterization. University of Michigan; 2020. doi: 10.7302/DY3H-SF31

27. Niu Y, Merza AM, Kadhem SI, et al. Evaluation of wind-solar hybrid power generation system based on Monte Carlo method. International Journal of Electrical and Computer Engineering. 2023; 13(4): 4401–4411. doi: 10.11591/ijece.v13i4.pp4401-4411 DOI: https://doi.org/10.11591/ijece.v13i4.pp4401-4411