Data-Driven Predictive Diagnostics and Fault-Tolerant Control for Fuel-Cell Electric Vehicle Powertrains Under Uncertainty
Downloads
Fuel-cell electric vehicles (FCEVs) are susceptible to sensor drift, actuator degradation and air path/water management faults that can quickly deteriorate efficiency, drivability and durability. This work introduces a control-oriented data-driven framework to integrate predictive diagnostics with FTC for FCEV powertrains subject to uncertainty. A multi-sensor feature pipeline comprising stack voltage/current, cathode pressure, compressor speed, hydrogen flow rate DC-link voltage and traction power is first established and the health indicators are generated via a probabilistic sequence model modeling temporal dependencies. The diagnostic module conducts an online detection and isolation of the faults in early stages with fault magnitude estimation for remaining useful time to predict constraint violation. Second, an active FTC layer allows real-time fault estimation–based control reconfiguration to update an uncertainty-aware powertrain controller by which fuel-cell ramp-rate limits, air-path constraints and energy-storage limits are enforced. The controller ensures that fast power transients are absorbed by the battery/supercapacitor, while keeping the fuel-cell system operational at high efficiencies and ensuring traction power tracking in addition to safe limits during faults. Uncertainty is dealt with by disturbance modeling and confidence-weighted adaptation to avoid overreacting to noisy diagnostic outputs. Simulation results for representative urban and aggressive drive cycles are presented, which incorporate introduced sensor bias, compressor efficiency loss and hydrogen starvation scenarios that show superior robustness compared with the non-tolerant 'baseline' in terms of increased fault detection lead time, no constraint or emissions coverage issues as well as efficient minimisation of hydrogen consumption while maintaining drivability. The considered combination of predictive diagnostics and FTC can thus offer a practical approach to reliable FCEV operation that will bring quantifiable safety and efficiency gains under real-world automotive scenarios.
Etienne Dijoux, Nadia Yousfi Steiner, Michel Benne, Marie-Cécile Péra, Brigitte Grondin Pérez, “A review of fault tolerant control strategies applied to proton exchange membrane fuel cell systems,” Journal of Power Sources, Volume 359, 2017, Pages 119-133, ISSN 0378-7753,
https://doi.org/10.1016/j.jpowsour.2017.05.058.
T. Escobet, D. Feroldi, S. de Lira, V. Puig, J. Quevedo, J. Riera, M. Serra, “Model-based fault diagnosis in PEM fuel cell systems,” Journal of Power Sources, Volume 192, Issue 1, 2009, Pages 216-223, ISSN 0378-7753, https://doi.org/10.1016/j.jpowsour.2008.12.014.
Z. Zheng, R. Petrone, M.C. Péra, D. Hissel, M. Becherif, C. Pianese, N. Yousfi Steiner, M. Sorrentino, “A review on non-model based diagnosis methodologies for PEM fuel cell stacks and systems,” International Journal of Hydrogen Energy, Volume 38, Issue 21, 2013, Pages 8914-8926, ISSN 0360-3199, https://doi.org/10.1016/j.ijhydene.2013.04.007.
Jingbo Wang, Bo Yang, Chunyuan Zeng, Yijun Chen, Zhengxun Guo, Danyang Li, Haoyin Ye, Ruining Shao, Hongchun Shu, Tao Yu, “Recent advances and summarization of fault diagnosis techniques for proton exchange membrane fuel cell systems: A critical overview,” Journal of Power Sources, Volume 500, 2021, 229932, ISSN 0378-7753, https://doi.org/10.1016/j.jpowsour.2021.229932.
Caizhi Zhang, Yuqi Zhang, Lei Wang, Xiaozhi Deng, Yang Liu, Jiujun Zhang, “A health management review of proton exchange membrane fuel cell for electric vehicles: Failure mechanisms, diagnosis techniques and mitigation measures,” Renewable and Sustainable Energy Reviews, Volume 182, 2023, 113369, ISSN 1364-0321,
https://doi.org/10.1016/j.rser.2023.113369.
Veza, Ibham. 2025. "Fuel-Cell Thermal Management Strategies for Enhanced Performance: Review of Fuel-Cell Thermal Management in Proton-Exchange Membrane Fuel Cells (PEMFCs) and Solid-Oxide Fuel Cells (SOFCs)" Hydrogen 6, no. 3: 65. https://doi.org/10.3390/hydrogen6030065.
Zihao Wang, Yan Gao, Jun Yu, Lei Tian, Cong Yin, “Data-driven fault diagnosis of PEMFC water management with segmented cell and deep learning technologies,” International Journal of Hydrogen Energy, Volume 67, 2024, Pages 715-727, ISSN 0360-3199,
https://doi.org/10.1016/j.ijhydene.2024.04.206.
Yangeng Chen, Jingjing Zhang, Shuang Zhai, Zhe Hu, “Data-driven modeling and fault diagnosis for fuel cell vehicles using deep learning,” Energy and AI, Volume 16, 2024, 100345, ISSN 2666-5468, https://doi.org/10.1016/j.egyai.2024.100345
Ming Zhang, Amirpiran Amiri, Yuchun Xu, Lucy Bastin, Tony Clark, “Self-adaptive digital twin of fuel cell for remaining useful lifetime prediction,” International Journal of Hydrogen Energy, Volume 89, 2024, Pages 634-647, ISSN 0360-3199, https://doi.org/10.1016/j.ijhydene.2024.09.266.
Nebeluk, Robert, and Maciej Ławryńczuk. 2022. "Fast Model Predictive Control of PEM Fuel Cell System Using the L1 Norm" Energies 15, no. 14: 5157. https://doi.org/10.3390/en15145157.
Vrlić, Martin, Daniel Ritzberger, and Stefan Jakubek. 2021. "Model-Predictive-Control-Based Reference Governor for Fuel Cells in Automotive Application Compared with Performance from a Real Vehicle" Energies 14, no. 8: 2206. https://doi.org/10.3390/en14082206.
Damiano Rotondo, Fatiha Nejjari, Vicenç Puig, “Fault tolerant control of a proton exchange membrane fuel cell using Takagi–Sugeno virtual actuators,” Journal of Process Control, Volume 45, 2016, Pages 12-29, ISSN 0959-1524, https://doi.org/10.1016/j.jprocont.2016.06.001.
Damiano Rotondo, Vicenç Puig, Fatiha Nejjari, “Fault Tolerant Control of a PEM Fuel Cell using qLPV Virtual Actuators,” IFAC-PapersOnLine, Volume 48, Issue 21, 2015, Pages 271-276, ISSN 2405-8963, https://doi.org/10.1016/j.ifacol.2015.09.539.
Vicenç Puig, Diego Feroldi, Maria Serra, Joseba Quevedo, Jordi Riera, “Fault-Tolerant MPC Control of PEM Fuel Cells,” IFAC Proceedings Volumes, Volume 41, Issue 2, 2008, Pages 11112-11117, ISSN 1474-6670, ISBN 9783902661005, https://doi.org/10.3182/20080706-5-KR-1001.01883.
J.H. Richter, W.P.M.H. Heemels, N. van de Wouw, J. Lunze, “Reconfigurable control of piecewise affine systems with actuator and sensor faults: Stability and tracking,” Automatica, Volume 47, Issue 4, 2011, Pages 678-691, ISSN 0005-1098, https://doi.org/10.1016/j.automatica.2011.01.048.
Sani, Mukhtar, Maxime Piffard, and Vincent Heiries. 2023. "Fault Detection for PEM Fuel Cells via Analytical Redundancy: A Critical Review and Prospects" Energies 16, no. 14: 5446.
https://doi.org/10.3390/en16145446.
J. Liu, Q. Li, W. Chen, Y. Yan and X. Wang, "A Fast Fault Diagnosis Method of the PEMFC System Based on Extreme Learning Machine and Dempster–Shafer Evidence Theory," in IEEE Transactions on Transportation Electrification, vol. 5, no. 1, pp. 271-284, March 2019, doi: 10.1109/TTE.2018.2886153.
Xuexia Zhang, Lishuo Peng, Fei He, Ruike Huang, “Fault diagnosis method of PEMFC system based on ensemble learning,” International Journal of Hydrogen Energy, Volume 69, 2024, Pages 1501-1510, ISSN 0360-3199, https://doi.org/10.1016/j.ijhydene.2024.05.139.
Xie, Jiaping, Chao Wang, Wei Zhu, and Hao Yuan. 2021. "A Multi-Stage Fault Diagnosis Method for Proton Exchange Membrane Fuel Cell Based on Support Vector Machine with Binary Tree" Energies 14, no. 20: 6526. https://doi.org/10.3390/en14206526.
Zhendong Sun, Yujie Wang, Zonghai Chen, “Fault diagnosis method for proton exchange membrane fuel cell system based on digital twin and unsupervised domain adaptive learning,” International Journal of Hydrogen Energy, Volume 50, Part C, 2024, Pages 1207-1219, ISSN 0360-3199, https://doi.org/10.1016/j.ijhydene.2023.10.148.
Zhongliang Li, Rachid Outbib, Stefan Giurgea, Daniel Hissel, Alain Giraud, Pascal Couderc, “Fault diagnosis for fuel cell systems: A data-driven approach using high-precise voltage sensors,” Renewable Energy, Volume 135, 2019, Pages 1435-1444, ISSN 0960-1481, https://doi.org/10.1016/j.renene.2018.09.077.
Tian, Ying, Qiang Zou, and Jin Han. 2021. "Data-Driven Fault Diagnosis for Automotive PEMFC Systems Based on the Steady-State Identification" Energies 14, no. 7: 1918. https://doi.org/10.3390/en14071918
Kang, Byungwoo, Wonbin Na, and Hyeongcheol Lee. 2022. "Model-Based Fault Analysis and Diagnosis of PEM Fuel Cell Control System" Applied Sciences 12, no. 24: 12733. https://doi.org/10.3390/app122412733.
Mounica, V., and Y. P. Obulesu. 2022. "Hybrid Power Management Strategy with Fuel Cell, Battery, and Supercapacitor for Fuel Economy in Hybrid Electric Vehicle Application" Energies 15, no. 12: 4185. https://doi.org/10.3390/en15124185.
Ji, Cong, Elkhatib Kamal, and Reza Ghorbani. 2024. "Reliable Energy Optimization Strategy for Fuel Cell Hybrid Electric Vehicles Considering Fuel Cell and Battery Health" Energies 17, no. 18: 4686. https://doi.org/10.3390/en17184686.
Zhao, X., Huang, W., Zhou, Y. et al. Enhanced fault detection in proton exchange membrane fuel cell via neural network model and sensitivity-based analysis. Sci. China Technol. Sci. 68, 2020105 (2025). https://doi.org/10.1007/s11431-025-2991-0.
Shu, Xing, Fengyan Yi, Jinming Zhang, Jiaming Zhou, Shuo Wang, Hongtao Gong, and Shuaihua Wang. 2025. "An Explainable Fault Diagnosis Algorithm for Proton Exchange Membrane Fuel Cells Integrating Gramian Angular Fields and Gradient-Weighted Class Activation Mapping" Electronics 14, no. 22: 4401. https://doi.org/10.3390/electronics14224401.
