Lifetime Prediction Analysis of Proton Exchange Membrane Fuel Cells Based on Empirical Mode Decomposition—Temporal Convolutional Network
Source abstract
Abstract
Proton exchange membrane fuel cells (PEMFCs) are ideal for fuel cell vehicles due to their high specific power, rapid start-up, and low operating temperatures. However, their limited lifespan presents a challenge for large-scale deployment. Accurate assessment of remaining useful life (RUL) is essential for enhancing longevity. Automotive PEMFC systems are complex and nonlinear, making lifespan prediction difficult. Recent studies suggest deep learning approaches hold promise for this task. This study proposes a novel EMD-TCN-GN algorithm, which, for the first time, integrates empirical mode decomposition (EMD), temporal convolutional network (TCN), and group normalization (GN) by using EMD to adaptively decompose non-stationary signals (such as voltage fluctuations), the dilated convolution of TCN to capture long-term dependencies, and combining GN to group-calibrate intrinsic mode function (IMF) features to solve the problems of modal aliasing and training instability. Parametric analysis shows optimal accuracy with the grouping parameter set to 4. Experimental validation, with a voltage lifetime threshold at 96% (3.228 V), shows the predicted degradation closely aligns with actual results. The model predicts voltage threshold times at 809 h and 876 h, compared to actual values of 807 h and 872 h, with a temporal prediction error margin of 0.250–0.460%. These results demonstrate the model’s high prediction fidelity and support proactive health management of PEMFC systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fuel Cells and Related Materials · Advanced Battery Technologies Research · Electric and Hybrid Vehicle Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Hubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan University of Technology, Wuhan 430070, China
Foshan Xianhu Laboratory of the Advanced Energy Science and Technology Guangdong Laboratory, Foshan 528200, China
Dongfeng Motor Corporation Research & Development Institute, Wuhan 430058, China
Funding
Foshan Xianhu Laboratory of the Advanced Energy Science and Technology Guangdong Laboratory · Key R&D project of Hubei Province, China
References (46)
Show source-provided references
1. Learning-based model predictive energy management for fuel cell hybrid electric bus with health-aware control10.1016/j.apenergy.2023.122228 ↗
2. Li, X., Ye, T., Meng, X., He, D., Li, L., Song, K., Jiang, J., and Sun, C. (2024). Advances in the Application of Sulfonated Poly(Ether Ether Ketone) (SPEEK) and Its Organic Composite Membranes for Proton Exchange Membrane Fuel Cells (PEMFCs). Polymers, 16.10.3390/polym16192840 ↗
3. Degradation Behaviors of Solid Oxide Fuel Cell Stacks in Steady-State and Cycling Conditions10.1021/acs.energyfuels.0c02920 ↗
4. A review on lifetime pre-diction of proton exchange membrane fuel cells system10.1016/j.jpowsour.2022.231256 ↗
5. A performance degradation prediction model for PEMFC based on bi-directional long short-term memory and multi-head self-attention mechanism10.1016/j.ijhydene.2024.02.181 ↗
6. Degradation Prediction of PEM Fuel Cell Stack Based on Multi-Physical Aging Model with Particle Filter Approach10.1109/TIA.2017.2680406 ↗
7. Hu, Z. (2019). Research on Durability Modeling and State Estimation of Automotive Fuel Cell Systems, Tsinghua University.
8. Extended Kalman Filter for prognostic of Proton Exchange Membrane Fuel Cell10.1016/j.apenergy.2015.11.071 ↗
9. An overview of fuel cell technology: Fundamentals and applications10.1016/j.rser.2014.01.012 ↗
10. Degradations analysis and modeling for health assessment and prognostics of PEMFC10.1016/j.ress.2015.12.003 ↗
11. Some improvments of Particle Filtering Based Prognosis for PEM Fuel Cell10.1016/j.ifacol.2016.11.028 ↗
12. Zhang, J., Yan, F., Du, C., Zhang, Y., Zheng, C., Wang, J., and Chen, B. (2024). A Multi-Feature Fusion Method for Life Prediction of Automotive Proton Exchange Membrane Fuel Cell Based on TCN-GRU. Materials, 17.10.20944/preprints202406.1368.v1 ↗
13. Liu, J. (2020). Research on Data-Driven Fault Diagnosis and Life Prediction Methods for PEMFC Power Generation Systems, Southwest Jiaotong University.
14. Transformer Based Long-Term Prognostics for Dynamic Operating PEM Fuel Cells10.1109/TTE.2023.3266803 ↗
15. A real-time prediction method for PEMFC life under actual operating conditions
16. Hierarchical porous carbon from mango seed husk for electro-chemical energy storage10.1016/j.ceja.2021.100158 ↗
17. A modified relevance vector machine for PEM fuel-cell stack aging prediction10.1109/TIA.2016.2524402 ↗
18. Morando, S., Jemei, S., Gourivrau, R., Zerhouni, N., and Hissel, D. (2014, January 27–30). Fuel Cells Remaining Useful Lifetime forecasting using Echo State Network. In Proceeding of the IEEE Vehicle Power and Propulsion Conference, Coimbra, Portugal.10.1109/VPPC.2014.7007074 ↗
19. Gated recurrent unit networks for remaininguseful life prediction10.1016/j.ifacol.2020.12.2795 ↗
20. Degradation prediction of proton exchange membrane fuel cell using auto-encoder based health indicator and long short-term memory network10.1016/j.ijhydene.2022.08.092 ↗
21. Remaining useful life prediction of PEMFC based on matrix long short-term memory10.1016/j.ijhydene.2025.02.302 ↗
22. A deep learning method based on CNN-BiGRU and attention mechanism for proton exchange membrane fuel cell performance degradation prediction10.1016/j.ijhydene.2024.11.127 ↗
23. Selection of optimal sensors for predicting performance of polymer electrolyte membrane fuel cell10.1016/j.jpowsour.2016.08.021 ↗
24. Uncertainty quantification of proton-exchange-membrane fuel cells degradation prediction based on Bayesian-Gated Recurrent Unit10.1016/j.etran.2023.100230 ↗
25. Li, Q., and Gao, Z. (2024, January 28–31). A Similarity-based prognostics approach for full cells state of health. In Proceeding of the Prognostics and System Health Management Conference, Zhangjiajie, China.
26. (2025, May 25). IEEE PHM Society. “PHM 2014 Data Challenge Dataset”, 2014. Available online: https://search-data.ubfc.fr/FR-18008901306731-2021-07-19_IEEE-PHM-Data-Challenge-2014.html.
27. Degradation prediction of proton exchange membrane fuel cell based on grey neural model and particle swarm optimization10.1016/j.enconman.2019.05.045 ↗
28. Research on the intrinsic mode function (IMF) criterion in EMD method10.1016/j.ymssp.2005.09.011 ↗
29. Time-of-use modeling and prediction of daily power transmission based on empirical mode decomposition and extreme learning machine
30. Li, P. (2021). Life Prediction Technology of Hydrogen Fuel Cell Based on Cyclic Neural Network, University of Electronic Science and Technology of China.
31. Optimization of a PEM fuel cell operating conditions: Obtaining the maximum performance polarization curve10.1016/j.ijhydene.2016.03.136 ↗
32. Remaining useful life estimation of engineered systems using vanilla LSTM neural networks10.1016/j.neucom.2017.05.063 ↗
33. Remaining useful life prediction of PEMFC based on long short-term memory recurrent neural networks10.1016/j.ijhydene.2018.10.042 ↗
34. Displacement prediction of Baijiabao landslide based on empirical mode decomposition and long short-term memory neural network in Three Gorges area, China10.1016/j.cageo.2017.10.013 ↗
35. Bayesian approach and time series dimensionality reduction to LSTM-based model-building for fault diagnosis of a reciprocating compressor10.1016/j.neucom.2019.11.006 ↗
36. Degradation prediction model for proton exchange membrane fuel cells based on long short-term memory neural network and Savitzky-Golay filter10.1016/j.ijhydene.2021.02.069 ↗
37. Main factors affecting the lifetime of Proton Exchange Membrane fuel cells in vehicle applications: A review10.1016/j.apenergy.2014.03.048 ↗
38. Ulyanov, D., Vedaldi, A., and Lempitsky, V. (2017, January 21–26). Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.437 ↗
39. A model with high-precision on proton exchange membrane fuel cell performance degradation prediction based on temporal convolutional network-long short-term memory10.1016/j.ijhydene.2024.06.095 ↗
40. Remaining useful life prediction of lithium-ion batteries based on TCN-DCN fusion model combined with IRRS filtering10.1016/j.est.2023.108586 ↗
41. A new dynamic predictive maintenance framework using deep learning for failure prognostics10.1016/j.ress.2019.03.018 ↗
42. Data-driven diagnosis of PEM fuel cell: A comparative study10.1016/j.conengprac.2014.02.019 ↗
43. Data-driven proton exchange membrane fuel cell degradation predication through deep learning method10.1016/j.apenergy.2018.09.111 ↗
44. An improved neural network model for predicting the remaining useful life of proton exchange membrane fuel cells10.1016/j.ijhydene.2023.03.219 ↗
45. A novel online degradation model for proton exchange membrane fuel cell based on online transfer learning10.1016/j.ijhydene.2022.12.260 ↗
46. Control strategy for the anode gas supply system in a proton exchange membrane fuel cell system10.1016/j.egyr.2023.10.079 ↗