IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v18y2025i10p2669-d1661270.html
   My bibliography  Save this article

Online Pre-Diagnosis of Multiple Faults in Proton Exchange Membrane Fuel Cells by Convolutional Neural Network Based Bi-Directional Long Short-Term Memory Parallel Model with Attention Mechanism

Author

Listed:
  • Junyi Chen

    (School of Aeronautics and Astronautics, Sun Yat-sen University, 135, Xingang Xi Road, Guangzhou 510275, China)

  • Huijun Ran

    (School of Aeronautics and Astronautics, Sun Yat-sen University, 135, Xingang Xi Road, Guangzhou 510275, China)

  • Ziyang Chen

    (School of Aeronautics and Astronautics, Sun Yat-sen University, 135, Xingang Xi Road, Guangzhou 510275, China)

  • Trevor Hocksun Kwan

    (School of Advanced Energy, Sun Yat-sen University, No.66, Gongchang Road, Guangming District, Shenzhen 518107, China)

  • Qinghe Yao

    (School of Aeronautics and Astronautics, Sun Yat-sen University, 135, Xingang Xi Road, Guangzhou 510275, China)

Abstract

Proton exchange membrane fuel cell (PEMFC) fault diagnosis faces two critical limitations: conventional offline methods lack real-time predictive capability, while existing prediction approaches are confined to single fault types. To address these gaps, this study proposes an online multi-fault prediction framework integrating three novel contributions: (1) a sensor fusion strategy leveraging existing thermal/electrochemical measurements (voltage, current, temperature, humidity, and pressure) without requiring embedded stack sensors; (2) a real-time sliding window mechanism enabling dynamic prediction updates every 1 s under variable load conditions; and (3) a modified CNN-based Bi-LSTM parallel model with attention mechanism (ConvBLSTM-PMwA) architecture featuring multi-input multi-output (MIMO) capability for simultaneous flooding/air-starvation detection. Through comparative analysis of different neural architectures using experimental datasets, the optimized ConvBLSTM-PMwA achieved 96.49% accuracy in predicting dual faults 64.63 s pre-occurrence, outperforming conventional LSTM models in both temporal resolution and long-term forecast reliability.

Suggested Citation

  • Junyi Chen & Huijun Ran & Ziyang Chen & Trevor Hocksun Kwan & Qinghe Yao, 2025. "Online Pre-Diagnosis of Multiple Faults in Proton Exchange Membrane Fuel Cells by Convolutional Neural Network Based Bi-Directional Long Short-Term Memory Parallel Model with Attention Mechanism," Energies, MDPI, vol. 18(10), pages 1-17, May.
    • Handle: RePEc:gam:jeners:v:18:y:2025:i:10:p:2669-:d:1661270
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/18/10/2669/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/18/10/2669/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Chen, Hui & Zhang, Zehui & Guan, Cong & Gao, Haibo, 2020. "Optimization of sizing and frequency control in battery/supercapacitor hybrid energy storage system for fuel cell ship," Energy, Elsevier, vol. 197(C).
    2. Wang, Junye, 2017. "System integration, durability and reliability of fuel cells: Challenges and solutions," Applied Energy, Elsevier, vol. 189(C), pages 460-479.
    3. Ren, Peng & Pei, Pucheng & Li, Yuehua & Wu, Ziyao & Chen, Dongfang & Huang, Shangwei & Jia, Xiaoning, 2019. "Diagnosis of water failures in proton exchange membrane fuel cell with zero-phase ohmic resistance and fixed-low-frequency impedance," Applied Energy, Elsevier, vol. 239(C), pages 785-792.
    4. Kim, Kyunghyun & Kim, Jaeyeon & Choi, Heesoo & Kwon, Obeen & Jang, Yujae & Ryu, Sangbong & Lee, Heeyun & Shim, Kyuhwan & Park, Taehyun & Cha, Suk Won, 2023. "Pre-diagnosis of flooding and drying in proton exchange membrane fuel cells by bagging ensemble deep learning models using long short-term memory and convolutional neural networks," Energy, Elsevier, vol. 266(C).
    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. Xiao, Fei & Chen, Tao & Gan, Zhongyu & Zhang, Ruixuan, 2023. "The influence of external operating conditions on membrane drying faults of proton-exchange membrane fuel cells," Energy, Elsevier, vol. 285(C).
    2. Li, Yuehua & Pei, Pucheng & Ma, Ze & Ren, Peng & Wu, Ziyao & Chen, Dongfang & Huang, Hao, 2019. "Characteristic analysis in lowering current density based on pressure drop for avoiding flooding in proton exchange membrane fuel cell," Applied Energy, Elsevier, vol. 248(C), pages 321-329.
    3. Nicu Bizon & Mircea Raceanu & Emmanouel Koudoumas & Adriana Marinoiu & Emmanuel Karapidakis & Elena Carcadea, 2020. "Renewable/Fuel Cell Hybrid Power System Operation Using Two Search Controllers of the Optimal Power Needed on the DC Bus," Energies, MDPI, vol. 13(22), pages 1-26, November.
    4. Olabi, A.G. & Wilberforce, Tabbi & Abdelkareem, Mohammad Ali, 2021. "Fuel cell application in the automotive industry and future perspective," Energy, Elsevier, vol. 214(C).
    5. Zhang, Tong & Wang, Peiqi & Chen, Huicui & Pei, Pucheng, 2018. "A review of automotive proton exchange membrane fuel cell degradation under start-stop operating condition," Applied Energy, Elsevier, vol. 223(C), pages 249-262.
    6. Reveles-Miranda, María & Ramirez-Rivera, Victor & Pacheco-Catalán, Daniella, 2024. "Hybrid energy storage: Features, applications, and ancillary benefits," Renewable and Sustainable Energy Reviews, Elsevier, vol. 192(C).
    7. Xie, Peilin & Tan, Sen & Bazmohammadi, Najmeh & Guerrero, Josep. M. & Vasquez, Juan. C. & Alcala, Jose Matas & Carreño, Jorge El Mariachet, 2022. "A distributed real-time power management scheme for shipboard zonal multi-microgrid system," Applied Energy, Elsevier, vol. 317(C).
    8. Eapen, Deepa Elizabeth & Suresh, Resmi & Patil, Sairaj & Rengaswamy, Raghunathan, 2021. "A systems engineering perspective on electrochemical energy technologies and a framework for application driven choice of technology," Renewable and Sustainable Energy Reviews, Elsevier, vol. 147(C).
    9. Pinthurat, Watcharakorn & Hredzak, Branislav, 2021. "Fully decentralized control strategy for heterogeneous energy storage systems distributed in islanded DC datacentre microgrid," Energy, Elsevier, vol. 231(C).
    10. Macias, A. & Kandidayeni, M. & Boulon, L. & Trovão, J.P., 2021. "Fuel cell-supercapacitor topologies benchmark for a three-wheel electric vehicle powertrain," Energy, Elsevier, vol. 224(C).
    11. Eryilmaz, Serkan & Devrim, Yilser, 2019. "Reliability and optimal replacement policy for a k-out-of-n system subject to shocks," Reliability Engineering and System Safety, Elsevier, vol. 188(C), pages 393-397.
    12. Li, Yuehua & Pei, Pucheng & Ma, Ze & Ren, Peng & Huang, Hao, 2020. "Analysis of air compression, progress of compressor and control for optimal energy efficiency in proton exchange membrane fuel cell," Renewable and Sustainable Energy Reviews, Elsevier, vol. 133(C).
    13. Huo, Sen & Cooper, Nathanial James & Smith, Travis Lee & Park, Jae Wan & Jiao, Kui, 2017. "Experimental investigation on PEM fuel cell cold start behavior containing porous metal foam as cathode flow distributor," Applied Energy, Elsevier, vol. 203(C), pages 101-114.
    14. Ren, Peng & Meng, Yining & Pei, Pucheng & Fu, Xi & Chen, Dongfang & Li, Yuehua & Zhu, Zijing & Zhang, Lu & Wang, Mingkai, 2023. "Rapid synchronous state-of-health diagnosis of membrane electrode assemblies in fuel cell stacks," Applied Energy, Elsevier, vol. 330(PA).
    15. Cai, Weiqiang & Zhou, Ruidong & Wang, Chenxia & Xie, Chao & Xiao, Liusheng & Zhang, Zhonggang & Yang, Chao & Yuan, Jinliang, 2025. "On characteristics and research development of coupled fuel cell stack performance and stress," Applied Energy, Elsevier, vol. 388(C).
    16. Ha, Chan & Jiao, Yi & Wang, Cong & Qin, Jiang & Wang, Sibo & Liu, He & Liu, Zekuan & Guo, Fafu, 2023. "Experimental study of hydrogen catalytic combustion wall temperature distribution characteristics and its effect on the coupling performance of autothermal reformers," Energy, Elsevier, vol. 271(C).
    17. Wang, Bowen & Deng, Hao & Jiao, Kui, 2018. "Purge strategy optimization of proton exchange membrane fuel cell with anode recirculation," Applied Energy, Elsevier, vol. 225(C), pages 1-13.
    18. Lu Zhang & Yongfeng Liu & Guijun Bi & Xintong Liu & Long Wang & Yuan Wan & Hua Sun, 2022. "Modeling and Experimental Investigation of the Anode Inlet Relative Humidity Effect on a PEM Fuel Cell," Energies, MDPI, vol. 15(13), pages 1-20, June.
    19. Zeng, Tao & Xiao, Long & Chen, Jinrui & Li, Yu & Yang, Yi & Huang, Shulong & Deng, Chenghao & Zhang, Caizhi, 2023. "Feedforward-based decoupling control of air supply for vehicular fuel cell system: Methodology and experimental validation," Applied Energy, Elsevier, vol. 335(C).
    20. Chiara Dall’Armi & Davide Pivetta & Rodolfo Taccani, 2023. "Hybrid PEM Fuel Cell Power Plants Fuelled by Hydrogen for Improving Sustainability in Shipping: State of the Art and Review on Active Projects," Energies, MDPI, vol. 16(4), pages 1-34, February.

    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:gam:jeners:v:18:y:2025:i:10:p:2669-:d:1661270. 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: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    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.