IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v406y2026ics0306261925020173.html

Explainable machine learning unveils a critical trade-off in SOFCs: The role of cathode-to-anode reaction site ratio

Author

Listed:
  • Duan, Li
  • Zhou, Yinghao
  • Yan, Zilin
  • Pan, Zehua
  • Zhong, Zheng

Abstract

Solid oxide fuel cell (SOFC) research recognizes the critical importance of electrode reaction sites for cell performance. This study, for the first time, systematically investigates the influence of the cathode to anode reaction site ratio, denoted as λ, on SOFC performance and reliability. The ratio λ is defined as the thickness scaled ratio of cathode double phase boundary (DPB) area to anode triple phase boundary (TPB) length. Using integrated experiments, multiphysical modeling, and explainable AI (XAI), we characterize the effects of λ on maximum power density and failure probability under various operating conditions. Results demonstrate that λ is the most significant factor affecting power density and substantially influences failure probability. A strong nonlinear relationship exists between λ and both metrics, with optimal λ shifting dynamically with temperature and gas flow. At higher temperatures (T≥1023.15 K) and sufficient flow (Q≥50 SCCM), λ of approximately 3000 nm enables high power density (>1.1 W/cm2) and low failure probability (<0.01). At T=973.15 K, maintaining λ near 1750 nm improves power output by over 15 %. This work reveals a fundamental performance reliability trade off governed by λ and identifies key microstructural parameters for both electrode optimization.

Suggested Citation

  • Duan, Li & Zhou, Yinghao & Yan, Zilin & Pan, Zehua & Zhong, Zheng, 2026. "Explainable machine learning unveils a critical trade-off in SOFCs: The role of cathode-to-anode reaction site ratio," Applied Energy, Elsevier, vol. 406(C).
  • Handle: RePEc:eee:appene:v:406:y:2026:i:c:s0306261925020173
    DOI: 10.1016/j.apenergy.2025.127287
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261925020173
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.apenergy.2025.127287?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.

    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:406:y:2026:i:c:s0306261925020173. 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.

    We have no bibliographic references for this item. You can help adding them by using 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.