Artificial-intelligence-guided design of ordered gas diffusion layers for high-performing fuel cells via Bayesian machine learning.

Journal: Nature communications
Published Date: Jul 15, 2025

Abstract

Rational design of gas diffusion layers (GDL) is an example of a long-standing pursuit to increase the power density and reduce the cost of proton exchange membrane fuel cells (PEMFC). However, current state-of-the-art GDLs are designed by trial-and-error, which is a time-consuming endeavor. Here, we propose a closed-loop workflow of Bayesian machine learning approach to guide the design of GDL structures. With artificial neural network accelerating the calculation of anisotropic transport properties of reconstructed GDLs, Bayesian optimization algorithm identifies optimal structures in only 40 steps, maximizing the PEMFC's limiting current density. Results suggest that the optimal porous GDL structure consists of highly orientated fibers with moderate diameters, which is successfully fabricated with a controlled electrospinning technique. The PEMFC demonstrates a high power density of 2.17 W cm and a limiting current density of ~7200 mA cm, far exceeding that with commercial GDL (1.33 W cm and ~2700 mA cm).

Authors

  • Jing Sun
    Department of Gastroenterology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
  • Pengzhu Lin
    Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong SAR 999077, China.
  • Lin Zeng
    Department of Health Management, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, China.
  • Zixiao Guo
    Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong SAR 999077, China.
  • Yuting Jiang
    Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Kowloon, China.
  • Cailin Xiao
    Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen, China.
  • Qinping Jian
    Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Kowloon, China.
  • Jiayou Ren
    Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Kowloon, China.
  • Lyuming Pan
    Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen, China.
  • Xiaosa Xu
    Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong SAR 999077, China.
  • Zheng Li
    Department of Integrated Pulmonology, Fourth Clinical Medical College of Xinjiang Medical University, Urumqi, Xinjiang, China.
  • Lei Wei
    MOE Key Laboratory of Bioinformatics and Bioinformatics Division of BNRIST, Department of Automation, Tsinghua University, Beijing 100084, China.
  • Tianshou Zhao
    Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong SAR 999077, China.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals