For proton exchange membrane fuel cell (PEMFC) prognostics, deploying deep learning models in real applications depends not only on the network architecture but also on carefully chosen hyperparameters and training strategies. Hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) models can attain high predictive accuracy, yet their sensitivity to practical implementation choices has not been systematically quantified. This work addresses that gap by performing a methodological assessment of a representative CNN–LSTM framework rather than proposing a new architecture. Using the static-load IEEE PHM 2014 FC1 dataset as a controlled benchmark, we examine how two key factors—sliding window length and training data partitioning—jointly affect short-term accuracy and long-term forecast stability. Our results show that the hybrid CNN–LSTM reduces the root mean square error (RMSE) of short-term voltage prediction by 49% compared with a standalone LSTM baseline. For recursive long-horizon lifetime forecasting, a moderately sized sliding window of 40 h is identified as optimal, keeping the remaining useful life prediction error within ±5 h. In addition, the model exhibits strong robustness with respect to training set size: once more than 500 h of data are used for training, the variation in RMSE remains below 0.001 V. By confining the analysis to a static-load test case, we isolate the influence of these implementation parameters and provide practical, data-driven guidance for configuring CNN–LSTM-based prognostic models in PEMFC health management. The proposed validation methodology can be extended in future work to dynamic-load scenarios.
| [1] |
Raga C, Barrado A, Lázaro A, et al.. Black-box model, identification technique and frequency analysis for PEM fuel cell with overshooted transient response. IEEE Trans. Power Electron., 2014, 29(10): 5334.
|
| [2] |
Petrone R, Zheng Z, Hissel D, et al.. A review on model-based diagnosis methodologies for PEMFCs. Int. J. Hydrog. Energy, 2013, 38(17): 7077.
|
| [3] |
Li XY, Zhang ZM, Zhuang XX, Jia ZT, Wang T. Electrolyte effects in electrocatalytic kinetics. Chin. J. Chem., 2024, 42(24): 3533.
|
| [4] |
Liu JM, Hu Q, Sabola S, Zhang Y, Du B, Wang XZ. Comparative review of corrosion-resistant coatings on metal bipolar plates of proton exchange membrane fuel cells. Int. J. Miner. Metall. Mater., 2024, 31(12): 2627.
|
| [5] |
Zhang JH, Luo XJ, Ding YY, Chang LQ, Dong CF. Effect of bipolar-plates design on corrosion, mass and heat transfer in proton-exchange membrane fuel cells and water electrolyzers: A review. Int. J. Miner. Metall. Mater., 2024, 31(7): 1599.
|
| [6] |
Guo XT, Jiang XN, Luo R, Su C, Wei T. Bimetallic-MOF derivatives enabled 3D carbon cloth as a lithium sponge for a high-performance lithium-metal anode. Chem. Commun., 2025, 61(69): 12956.
|
| [7] |
F.Y. Cai, S.S. Cai, and Z.K. Tu, Proton exchange membrane fuel cell (PEMFC) operation in high current density (HCD): Problem, progress and perspective, Energy Convers. Manage., 307(2024), art. No. 118348.
|
| [8] |
Choi P, Jalani NH, Thampan TM, Datta R. Consideration of thermodynamic, transport, and mechanical properties in the design of polymer electrolyte membranes for higher temperature fuel cell operation. J. Polym. Sci. Part B: Polym. Phys., 2006, 44(16): 2183.
|
| [9] |
Kamiya M, Saito S, Ohmine I. Proton transfer and associated molecular rearrangements in the photocycle of photoactive yellow protein: Role of water molecular migration on the proton transfer reaction. J. Phys. Chem. B, 2007, 111(11): 2948.
|
| [10] |
Kreuer KD. On the complexity of proton conduction phenomena. Solid State Ionics, 2000, 136: 149.
|
| [11] |
Seo D, Park S, Jeon Y, Choi SW, Shul YG. Physical degradation of MEA in PEM fuel cell by on/off operation under nitrogen atmosphere. Korean J. Chem. Eng., 2010, 27(1): 104.
|
| [12] |
Tang HL, Shen PK, Jiang SP, Wang F, Pan M. A degradation study of Nafion proton exchange membrane of PEM fuel cells. J. Power Sources, 2007, 170(1): 85.
|
| [13] |
A.V. Virkar and Y.K. Zhou, Mechanism of catalyst degradation in proton exchange membrane fuel cells, J. Electrochem. Soc., 154(2007), No. 6, art. No. B540.
|
| [14] |
R.M. Darling and J.P. Meyers, Kinetic model of platinum dissolution in PEMFCs, J. Electrochem. Soc., 150(2003), No. 11, art. No. A1523.
|
| [15] |
E. Guilminot, A. Corcella, F. Charlot, F. Maillard, and M. Chatenet, Detection of Ptz+ ions and Pt nanoparticles inside the membrane of a used PEMFC, J. Electrochem. Soc., 154(2007), No. 1, art. No. B96.
|
| [16] |
Jouin M, Gouriveau R, Hissel D, Péra MC, Zerhouni N. Prognostics and health management of PEMFC–State of the art and remaining challenges. Int. J. Hydrogen Energy, 2013, 38(35): 15307.
|
| [17] |
Varde PV, Tian J, Pecht MG. Prognostics and health management based refurbishment for life extension of electronic systems. 2014 IEEE International Conference on Information and Automation (ICIA), 20141260.
|
| [18] |
Peng Y, Liu DT. Data-driven prognostics and health management: A review of recent advances. Chin. J. Sci. Instrum., 2014, 35(3): 481
|
| [19] |
Zhao DD, Gao F, Massonnat P, Dou MF, Miraoui A. Parameter sensitivity analysis and local temperature distribution effect for a PEMFC system. IEEE Trans. Energy Convers., 2015, 30(3): 1008.
|
| [20] |
Z.G. Hua, Z.X. Zheng, E. Pahon, M.C. Péra, and F. Gao, A review on lifetime prediction of proton exchange membrane fuel cells system, J. Power Sources, 529(2022), art. No. 231256.
|
| [21] |
Chen K, Laghrouche S, Djerdir A. Degradation prediction of proton exchange membrane fuel cell based on grey neural network model and particle swarm optimization. Energy Convers. Manage., 2019, 195: 810.
|
| [22] |
T. Wilberforce and A.G. Olabi, Performance prediction of proton exchange membrane fuel cells (PEMFC) using adaptive neuro inference system (ANFIS), Sustainability, 12(2020), No. 12, art. No. 4952.
|
| [23] |
Ma R, Li ZL, Breaz E, et al.. Data-fusion prognostics of proton exchange membrane fuel cell degradation. IEEE Trans. Ind. Appl., 2019, 55(4): 4321.
|
| [24] |
Z. Tian, Z. Wei, J.H. Wang, et al., Research progress on aging prediction methods for fuel cells: Mechanism, methods, and evaluation criteria, Energies, 16(2023), No. 23, art. No. 7750.
|
| [25] |
Z.D. Zhang, Y.X. Wang, H.W. He, and F.C. Sun, A short- and long-term prognostic associating with remaining useful life estimation for proton exchange membrane fuel cell, Appl. Energy, 304(2021), art. No. 117841.
|
| [26] |
W.C. Zhu, B.X. Guo, Y. Li, et al., Uncertainty quantification of proton-exchange-membrane fuel cells degradation prediction based on Bayesian-Gated Recurrent Unit, eTransportation, 16(2023), art. No. 100230.
|
| [27] |
B. Ghojogh and A. Ghodsi, Recurrent neural networks and long short-term memory networks: Tutorial and survey, 2023. https://doi.org/10.48550/arXiv.2304.11461
|
| [28] |
Zhao DC, Jiang RP, Feng MY, et al.. A deep learning algorithm based on 1D CNN-LSTM for automatic sleep staging. Technol. Health Care, 2022, 30(2): 323.
|
| [29] |
Ma M, Mao Z. Deep-convolution-based LSTM network for remaining useful life prediction. IEEE Trans. Ind. Inform., 2021, 17(3): 1658.
|
| [30] |
Y.Y. Ma, S.T. Li, S.L. Zhou, et al., Performance degradation prediction of proton exchange membrane fuel cells based on CNN-LSTM network with squeeze-and-excitation attention mechanism, Energy, 335(2025), art. No. 138127.
|
RIGHTS & PERMISSIONS
University of Science and Technology Beijing
PDF
