IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v402y2025ipas0306261925016058.html

A novel framework combining optimized data decomposition and multimodal hybrid neural network Res-CGA for fuel cell performance degradation prognostics

Author

Listed:
  • Hu, Baobao
  • Qu, Zhiguo
  • Song, Yukun
  • Wang, Keyong
  • Hou, Zhongjun

Abstract

Proton exchange membrane fuel cell (PEMFC) degradation involves complex interactions among multiple aging mechanisms, presenting challenges for accurate voltage prediction due to nonlinear dynamics and stochastic features. This study proposes a framework combining optimized data decomposition and multimodal hybrid neural network Res-CGA for PEMFC voltage degradation prognostics. It develops an optimized decomposition technique integrating the slime mold algorithm with variational mode decomposition to iteratively decompose aging voltage data into time-varying intrinsic mode functions (IMFs). Subsequently, entropy-driven k-means clustering consolidates IMFs into three cooperative IMFs: high-frequency, low-frequency, and trend sequences. The dedicated hybrid neural network Res-CGA (incorporating residual connections, convolutional operations, gating mechanisms, and attention mechanisms) is developed to learn decomposed features. The proposed method demonstrates superior capability in resolving multi-factor superimposed aging features and strong nonstationary. It effectively extracts trend features, long-period patterns, and high time-varying characteristics from aging voltage data, thereby achieving high-precision predictions. Validated across four independent PEMFC aging datasets, the framework achieves satisfactory accuracy with normalized root mean square error (NRMSE) < 0.05 and normalized mean absolute percentage error (NMAPE) < 10 %, outperforming benchmark machine learning and deep learning models by >3.94 % NRMSE and >1.68 % NMAPE reductions. Ablation studies confirm the critical contributions of the optimized decomposition module, the Res-CGA model, and the high-frequency sequence re-decomposition in the proposed method. These modules improve precision of the proposed method, achieving >0.41 % NRMSE and >0.20 % NMAPE reductions. This work establishes a novel technical pathway for PEMFC performance degradation prediction. Future research will focus on integrating this framework into prognostic and health management systems to validate its engineering applicability.

Suggested Citation

  • Hu, Baobao & Qu, Zhiguo & Song, Yukun & Wang, Keyong & Hou, Zhongjun, 2025. "A novel framework combining optimized data decomposition and multimodal hybrid neural network Res-CGA for fuel cell performance degradation prognostics," Applied Energy, Elsevier, vol. 402(PA).
    • Handle: RePEc:eee:appene:v:402:y:2025:i:pa:s0306261925016058
    DOI: 10.1016/j.apenergy.2025.126875
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261925016058
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.apenergy.2025.126875?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Liu, Ze & Xu, Sichuan & Zhao, Honghui & Wang, Yupeng, 2022. "Durability estimation and short-term voltage degradation forecasting of vehicle PEMFC system: Development and evaluation of machine learning models," Applied Energy, Elsevier, vol. 326(C).
    2. Chen, Kui & Laghrouche, Salah & Djerdir, Abdesslem, 2019. "Degradation model of proton exchange membrane fuel cell based on a novel hybrid method," Applied Energy, Elsevier, vol. 252(C), pages 1-1.
    3. Zuo, Jian & Lv, Hong & Zhou, Daming & Xue, Qiong & Jin, Liming & Zhou, Wei & Yang, Daijun & Zhang, Cunman, 2021. "Deep learning based prognostic framework towards proton exchange membrane fuel cell for automotive application," Applied Energy, Elsevier, vol. 281(C).
    4. Bressel, Mathieu & Hilairet, Mickael & Hissel, Daniel & Ould Bouamama, Belkacem, 2016. "Extended Kalman Filter for prognostic of Proton Exchange Membrane Fuel Cell," Applied Energy, Elsevier, vol. 164(C), pages 220-227.
    5. Ma, Rui & Yang, Tao & Breaz, Elena & Li, Zhongliang & Briois, Pascal & Gao, Fei, 2018. "Data-driven proton exchange membrane fuel cell degradation predication through deep learning method," Applied Energy, Elsevier, vol. 231(C), pages 102-115.
    6. Zhang, Caizhi & Zhang, Yuqi & Wang, Lei & Deng, Xiaozhi & Liu, Yang & Zhang, Jiujun, 2023. "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, Elsevier, vol. 182(C).
    7. Zhou, Feite & Huang, Zhehao & Zhang, Changhong, 2022. "Carbon price forecasting based on CEEMDAN and LSTM," Applied Energy, Elsevier, vol. 311(C).
    8. Örnek, Bülent Nafi & Aydemir, Salih Berkan & Düzenli, Timur & Özak, Bilal, 2022. "A novel version of slime mould algorithm for global optimization and real world engineering problems," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 198(C), pages 253-288.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Chen, Kui & Badji, Abderrezak & Laghrouche, Salah & Djerdir, Abdesslem, 2022. "Polymer electrolyte membrane fuel cells degradation prediction using multi-kernel relevance vector regression and whale optimization algorithm," Applied Energy, Elsevier, vol. 318(C).
    2. Tian, Lei & Gao, Yan & Yang, Haiyu & Wang, Renkang, 2025. "Multi-scenario long-term degradation prediction of PEMFC based on generative inference informer model," Applied Energy, Elsevier, vol. 377(PA).
    3. Zuo, Jian & Steiner, Nadia Yousfi & Li, Zhongliang & Hissel, Daniel, 2024. "Health management review for fuel cells: Focus on action phase," Renewable and Sustainable Energy Reviews, Elsevier, vol. 201(C).
    4. Chen, Li & Yang, Jibin & Wu, Xiaohua & Deng, Pengyi & Xu, Xiaohui & Peng, Yiqiang, 2025. "Remaining useful life prediction of PEMFCs based on mode decomposition and hybrid method under real-world traffic conditions," Energy, Elsevier, vol. 314(C).
    5. Zhuang Tian & Zheng Wei & Jinhui Wang & Yinxiang Wang & Yuwei Lei & Ping Hu & S. M. Muyeen & Daming Zhou, 2023. "Research Progress on Aging Prediction Methods for Fuel Cells: Mechanism, Methods, and Evaluation Criteria," Energies, MDPI, vol. 16(23), pages 1-21, November.
    6. Deng, Zhihua & Chan, Siew Hwa & Chen, Qihong & Liu, Hao & Zhang, Liyan & Zhou, Keliang & Tong, Sirui & Fu, Zhichao, 2023. "Efficient degradation prediction of PEMFCs using ELM-AE based on fuzzy extension broad learning system," Applied Energy, Elsevier, vol. 331(C).
    7. Wang, Fu-Kwun & Kebede, Getnet Awoke & Lo, Shih-Che & Woldegiorgis, Bereket Haile, 2024. "An embedding layer-based quantum long short-term memory model with transfer learning for proton exchange membrane fuel stack remaining useful life prediction," Energy, Elsevier, vol. 308(C).
    8. Yu, Yulong & Zheng, Qiang & Zhang, Tianyi & Li, Zhengyan & Chen, Lei & Tao, Wen-Quan, 2025. "Forecasting the output performance of PEMFCs via a novel deep learning framework considering varying operating conditions and time scales," Applied Energy, Elsevier, vol. 389(C).
    9. He, Wenbin & Liu, Ting & Ming, Wuyi & Li, Zongze & Du, Jinguang & Li, Xiaoke & Guo, Xudong & Sun, Peiyan, 2024. "Progress in prediction of remaining useful life of hydrogen fuel cells based on deep learning," Renewable and Sustainable Energy Reviews, Elsevier, vol. 192(C).
    10. Tao, Zihan & Zhang, Chu & Xiong, Jinlin & Hu, Haowen & Ji, Jie & Peng, Tian & Nazir, Muhammad Shahzad, 2023. "Evolutionary gate recurrent unit coupling convolutional neural network and improved manta ray foraging optimization algorithm for performance degradation prediction of PEMFC," Applied Energy, Elsevier, vol. 336(C).
    11. Chou, Jia-Hong & Wang, Fu-Kwun, 2025. "Future prediction on the remaining useful life of proton exchange membrane fuel using temporal fusion transformer model," Renewable Energy, Elsevier, vol. 247(C).
    12. Deng, Huiwen & Hu, Weihao & Cao, Di & Chen, Weirong & Huang, Qi & Chen, Zhe & Blaabjerg, Frede, 2022. "Degradation trajectories prognosis for PEM fuel cell systems based on Gaussian process regression," Energy, Elsevier, vol. 244(PA).
    13. Zhang, Zhendong & Wang, Ya-Xiong & He, Hongwen & Sun, Fengchun, 2021. "A short- and long-term prognostic associating with remaining useful life estimation for proton exchange membrane fuel cell," Applied Energy, Elsevier, vol. 304(C).
    14. Liu, Hao & Chen, Jian & Hissel, Daniel & Lu, Jianguo & Hou, Ming & Shao, Zhigang, 2020. "Prognostics methods and degradation indexes of proton exchange membrane fuel cells: A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 123(C).
    15. Aihua Tang & Yuanhang Yang & Quanqing Yu & Zhigang Zhang & Lin Yang, 2022. "A Review of Life Prediction Methods for PEMFCs in Electric Vehicles," Sustainability, MDPI, vol. 14(16), pages 1-18, August.
    16. Liu, Ze & Xu, Sichuan & Zhao, Honghui & Wang, Yupeng, 2022. "Durability estimation and short-term voltage degradation forecasting of vehicle PEMFC system: Development and evaluation of machine learning models," Applied Energy, Elsevier, vol. 326(C).
    17. Qiang Liu & Weihong Zang & Wentao Zhang & Yang Zhang & Yuqi Tong & Yanbiao Feng, 2025. "Steady-State Model Enabled Dynamic PEMFC Performance Degradation Prediction via Recurrent Neural Network," Energies, MDPI, vol. 18(10), pages 1-20, May.
    18. Song, Ke & Ding, Yuhang & Hu, Xiao & Xu, Hongjie & Wang, Yimin & Cao, Jing, 2021. "Degradation adaptive energy management strategy using fuel cell state-of-health for fuel economy improvement of hybrid electric vehicle," Applied Energy, Elsevier, vol. 285(C).
    19. Yue, Meiling & Jemei, Samir & Zerhouni, Noureddine & Gouriveau, Rafael, 2021. "Proton exchange membrane fuel cell system prognostics and decision-making: Current status and perspectives," Renewable Energy, Elsevier, vol. 179(C), pages 2277-2294.
    20. Desantes, J.M. & Novella, R. & Pla, B. & Lopez-Juarez, M., 2022. "A modeling framework for predicting the effect of the operating conditions and component sizing on fuel cell degradation and performance for automotive applications," Applied Energy, Elsevier, vol. 317(C).

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:appene:v:402:y:2025:i:pa:s0306261925016058. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/description#description .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.