Data-driven cross-condition optimization of membrane-electrode assembly performance of proton exchange membrane fuel cells

LI Mingzhe; YANG Liu; FU Kaihao; LI Ping; CAO Chenxi

doi:10.11949/0438-1157.20251355

您当前的位置：

首页 >

文章列表页 >

Data-driven cross-condition optimization of membrane-electrode assembly performance of proton exchange membrane fuel cells

Intelligent process engineering | 更新时间：2026-08-13

- Data-driven cross-condition optimization of membrane-electrode assembly performance of proton exchange membrane fuel cells
- CIESC Journal Vol. 77, Issue 6, Pages: 3526-3544(2026)
- 作者机构：
  
  1.华东理工大学能源化工过程智能制造教育部重点实验室，上海 200237
  2.华东理工大学化工学院，绿色化工与工业催化全国重点实验室，上海 200237
- 作者简介：
- 基金信息：
- DOI：10.11949/0438-1157.20251355
  CLC： TM 911.4
- Received：30 November 2025，
  
  Revised：2026-02-05，
  
  Online First：29 July 2026，
  
  Published：25 June 2026
- 稿件说明：
移动端阅览
李明哲, 杨柳, 付凯豪, 李平, 曹晨熙. 数据驱动的质子交换膜燃料电池膜电极性能跨工况优化[J]. 化工学报, 2026, 77(6): 3526-3544

LI Mingzhe, YANG Liu, FU Kaihao, LI Ping, CAO Chenxi. Data-driven cross-condition optimization of membrane-electrode assembly performance of proton exchange membrane fuel cells[J]. CIESC Journal, 2026, 77(6): 3526-3544
李明哲, 杨柳, 付凯豪, 李平, 曹晨熙. 数据驱动的质子交换膜燃料电池膜电极性能跨工况优化[J]. 化工学报, 2026, 77(6): 3526-3544 DOI： 10.11949/0438-1157.20251355.

LI Mingzhe, YANG Liu, FU Kaihao, LI Ping, CAO Chenxi. Data-driven cross-condition optimization of membrane-electrode assembly performance of proton exchange membrane fuel cells[J]. CIESC Journal, 2026, 77(6): 3526-3544 DOI： 10.11949/0438-1157.20251355.

摘要

质子交换膜燃料电池（proton exchange membrane fuel cell， PEMFC）低温适应性问题严重制约了其大范围商业应用。膜电极性质是决定PEMFC冷启动性能的根本因素，然而针对冷启动调优膜电极往往导致常规工况性能下降。本文提出了一种数据驱动的PEMFC膜电极跨工况优化设计框架，对阴、阳极催化层的关键组成和结构参数采样构建高保真机理数据集，训练了基于支持向量机、高斯过程回归、径向基神经网络等方法的代理模型，对冷启动性能关键指标的预测

均值达0.968，同时在常温性能预测中表现出很强的泛化能力。结合AI（artificial intelligence）代理模型与NSGA-Ⅲ（third-generation non-dominated sorting genetic algorithm）算法有效权衡膜电极的跨工况性能，优化的膜电极性质参数可提升PEMFC冷启动持续时长29.6%、最大温升11.9%，或在维持低温耐受性下提升常规工况最大功率密度3.6%，为PEMFC膜电极的高效理性设计及快速产品迭代提供了重要的理论依据与技术支持。

Abstract

The low-temperature adaptability of proton exchange membrane fuel cells (PEMFC) severely restricts their widespread commercial application. The properties of the membrane electrode assembly (MEA) are the fundamental factors determining the cold start performance of PEMFCs. However

optimizing the MEA for cold start often leads to a decline in performance under conventional conditions. This paper proposes a data-driven cross-condition optimization design framework for MEA of PEMFCs. A high-fidelity mechanism dataset is constructed by sampling key components and structural parameters of the anode and cathode catalyst layers. A surrogate model based on support vector machine

Gaussian process regression

and radial basis function neural network is trained

achieving a mean

² of 0.968 for key cold-start performance indicators

while also demonstrating strong generalization ability in room-temperature performance prediction. By integrating the AI surrogate model with the NSGA-Ⅲ algorithm

the cross-condition performance of the MEA is effectively balanced. Optimized MEA property parameters can enhance the PEMFC cold start duration by 29.6% and the maximum temperature rise by 11.9%. Alternatively

maintaining low-temperature tolerance while increasing the maximum power density under conventional conditions by 3.6%

providing crucial theoretical basis and technical support for efficient rational design and rapid product iteration of MEA of PEMFCs.

关键词

Keywords

references

Jiao K , Xuan J , Du Q , et al . Designing the next generation of proton-exchange membrane fuel cells [J ] . Nature , 2021 , 595 ( 7867 ): 361 - 369 .

Yu Y S , Zheng W B , Li B , et al . A comprehensive review of cold start in proton-exchange membrane fuel cells: challenges, strategies, and prospects [J ] . Applied Energy , 2025 , 390 : 125846 .

Mancino A N , Menale C , Vellucci F , et al . PEM fuel cell applications in road transport [J ] . Energies , 2023 , 16 ( 17 ): 6129 .

Luo Y Q , Jiao K . Cold start of proton exchange membrane fuel cell [J ] . Progress in Energy and Combustion Science , 2018 , 64 : 29 - 61 .

Choi Y , Kim M , Park J , et al . Proton exchange membrane fuel cell stack durability prediction using Arrhenius-based accelerated degradation model [J ] . Applied Sciences , 2025 , 15 ( 3 ): 1300

国家市场监督管理总局 , 国家标准化管理委员会 . 燃料电池发动机性能试验方法 : GB/T 24554—2022 [S ] . 北京 : 中国标准出版社 , 2022 .

State Administration for Market Regulation , Standardization Administration of the People's Republic of China . Performance test methods for fuel cell system : GB/T 24554—2022 [S ] . Beijing : Standards Press of China , 2022 .

Yang L , Fu K H , Jin X S , et al . Catalyst layer design with inhomogeneous distribution of platinum and ionomer optimal for proton exchange membrane fuel cell cold-start [J ] . Chemical Engineering Science , 2022 , 263 : 118132 .

Xie X , Zhang G B , Zhou J X , et al . Experimental and theoretical analysis of ionomer/carbon ratio effect on PEM fuel cell cold start operation [J ] . International Journal of Hydrogen Energy , 2017 , 42 ( 17 ): 12521 - 12530 .

Hou Y Z , Deng H , Pan F W , et al . Pore-scale investigation of catalyst layer ingredient and structure effect in proton exchange membrane fuel cell [J ] . Applied Energy , 2019 , 253 : 113561 .

Oberholzer P , Boillat P , Siegrist R , et al . Cold-start of a PEFC visualized with high resolution dynamic in-plane neutron imaging [J ] . Journal of the Electrochemical Society , 2011 , 159 ( 2 ): B235 - B245 .

Yoshimune W , Higuchi Y , Song F Z , et al . Neutron imaging for automotive polymer electrolyte fuel cells during rapid cold starts [J ] . Physical Chemistry Chemical Physics , 2024 , 26 ( 47 ): 29466 - 29474 .

Yang L , Cao C X , Gan Q Q , et al . Revealing failure modes and effect of catalyst layer properties for PEM fuel cell cold start using an agglomerate model [J ] . Applied Energy , 2022 , 312 : 118792 .

Yang L , Ma Z J , Gan Q Q , et al . Enhanced operational performance of PEM fuel cells with porous-carbon catalyst support: a multiscale modeling approach [J ] . Energy Conversion and Management , 2023 , 281 : 116858 .

Liang J Q , Fan L H , Du Q , et al . Ice formation during PEM fuel cell cold start: acceptable or not? [J ] . Advanced Science , 2023 , 10 ( 24 ): 2302151 .

Ding R , Wang R , Ding Y Q , et al . Designing AI-aided analysis and prediction models for nonprecious metal electrocatalyst-based proton-exchange membrane fuel cells [J ] . Angewandte Chemie International Edition , 2020 , 59 ( 43 ): 19175 - 19183 .

Zhang C Z , Shao Y F , Deng S F , et al . Multi-objective optimization of operating parameters of proton exchange membrane fuel cells by coupling surrogate model and intelligent algorithm [J ] . Fuel Cells , 2025 , 25 ( 6 ): e70033 .

Zhao J , Wei W , Zhao L , et al . Multi-objective optimization of PEMFC performance at different altitudes through integrated RSM, <math id="M48"><mi mathvariant="normal">N</mi><mi mathvariant="normal">S</mi><mi mathvariant="normal">G</mi><mi mathvariant="normal">A</mi><mo>-</mo><mi mathvariant="normal">Ⅱ</mi><mo>,</mo></math> https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=115523988&type= https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=115523976&type= 14.05466747 2.62466669 EWM, and TOPSIS methodology [J ] . International Journal of Hydrogen Energy , 2025 , 177 : 151615 .

Shi L , Du C , Zhou J L , et al . Optimization of fuel cell shutdown purge strategy based on machine learning: mechanism analysis and experimental verification [J ] . Renewable Energy , 2025 , 248 : 123165 .

Yang S , Zhu J Q , Deng C W , et al . Machine learning and computational modeling informed cold-start design and optimization for proton exchange membrane fuel cells with cathode catalytic H 2 -O 2 reaction heating [J ] . ENGINEERING Chemical Engineering , 2026 , 20 ( 3 ): 19 .

Wang B W , Xie B , Xuan J , et al . AI-based optimization of PEM fuel cell catalyst layers for maximum power density via data-driven surrogate modeling [J ] . Energy Conversion and Management , 2020 , 205 : 112460 .

Li H W , Xu B S , Lu G L , et al . Multi-objective optimization of PEM fuel cell by coupled significant variables recognition, surrogate models and a multi-objective genetic algorithm [J ] . Energy Conversion and Management , 2021 , 236 : 114063 .

Siddiqa S , Chang K , Naqvi S B , et al . AI-assisted proton exchange membrane (PEM) fuel cell performance prediction using CFD and data-driven surrogate models [J ] . International Communications in Heat and Mass Transfer , 2024 , 156 : 107616

Yu X S , Zhang J Y , Zhang J , et al . Cold start optimization study of PEMFC low temperature coolant-assisted heating based on CAB-net and LO-WOA [J ] . Hydrogen , 2026 , 7 ( 1 ): 24 .

Liu Z W , Mao X P , Kang Z H , et al . Multi-objective optimization of ice distribution uniformity and startup failure time for cold start of PEMFC catalyst layer based on CTnet and PSO-GA [J ] . Fuel , 2024 , 363 : 130922 .

付佳丽 . 大气低频振荡对华北冬季强降温事件影响研究 [D ] . 南京 : 南京信息工程大学 , 2021 .

Fu J L . Study on the influence of atmospheric low-frequency oscillation on severe cooling events in winter in North China [D ] . Nanjing : Nanjing University of Information Science & Technology , 2021 .

Mishler J , Wang Y , Lujan R , et al . An experimental study of polymer electrolyte fuel cell operation at sub-freezing temperatures [J ] . Journal of the Electrochemical Society , 2013 , 160 ( 6 ): F514 - F521 .

Yakovlev Y V , Lobko Y V , Vorokhta M , et al . Ionomer content effect on charge and gas transport in the cathode catalyst layer of proton-exchange membrane fuel cells [J ] . Journal of Power Sources , 2021 , 490 : 229531 .

COMSOL AB . COMSOL Multiphysics [CP/OL ] . 5.6. Stockholm: COMSOL AB , 2020 [ 2025-11-20 ] . http://www.comsol.com/ http://www.comsol.com/ .

Schenk O , Gärtner K . Solving unsymmetric sparse systems of linear equations with PARDISO [J ] . Future Generation Computer Systems , 2004 , 20 ( 3 ): 475 - 487 .

Metropolis N , Rosenbluth A W , Rosenbluth M N , et al . Equation of state calculations by fast computing machines [J ] . The Journal of Chemical Physics , 1953 , 21 ( 6 ): 1087 - 1092 .

McKay M D , Beckman R J , Conover W J . A comparison of three methods for selecting values of input variables in the analysis of output from a computer code [J ] . Technometrics , 2000 , 42 ( 1 ): 55 - 61 .

Pedregosa F , Varoquaux G , Gramfort A , et al . Scikit-learn: machine learning in Python [J ] . Journal of Machine Learning Research , 2011 , 12 : 2825 - 2830 .

Drucker H , Burges C J C , Kaufman L , et al . Support vector regression machines [C ] // Proceedings of the 10th International Conference on Neural Information Processing Systems . New York : ACM , 1996 : 155 - 161 .

Rasmussen C E , Williams C K I . Gaussian Processes for Machine Learning [M ] . Cambridge, MA : MIT Press , 2006 .

Broomhead D S , Lowe D . Multivariable functional interpolation and adaptive networks [J ] . Complex Syst. , 1988 , 2 ( 3 ): 321 - 355 .

Friedman J H . Greedy function approximation: a gradient boosting machine [J ] . The Annals of Statistics , 2001 , 29 ( 5 ): 1189 - 1232 .

Chen T Q , Guestrin C . XGBoost: a scalable tree boosting system [C ] // Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . New York : ACM , 2016 : 785 - 794 .

Prokhoenkova L , Gusev G , Vorobev A , et al . CatBoost: unbiased boosting with categorical features [C ] // Advances in Neural Information Processing Systems31 . Red Hook : Curran Associates . 2018 : 6639 - 6649 .

Deb K , Pratap A , Agarwal S , et al . A fast and elitist multiobjective genetic algorithm: NSGA-Ⅱ [J ] . IEEE Transactions on Evolutionary Computation , 2002 , 6 ( 2 ): 182 - 197 .

Das I , Dennis J E . Normal-boundary intersection: a new method for generating the Pareto surface in nonlinear multicriteria optimization problems [J ] . SIAM Journal on Optimization , 1998 , 8 ( 3 ): 631 - 657 .

Geatpy Team . Geatpy: A High-performance Evolutionary Algorithm Toolkit for Python [CP/OL ] . GitHub , 2023 . https://github.com/geatpy-dev/geatpy https://github.com/geatpy-dev/geatpy .

Tzeng G H , Huang J J . Multiple Attribute Decision Making: Methods and Applications [M ] . Boca Raton : CRC Press , 2011 .

Sassin M B , Garsany Y , Atkinson R W , et al . Understanding the interplay between cathode catalyst layer porosity and thickness on transport limitations en route to high-performance PEMFCs [J ] . International Journal of Hydrogen Energy , 2019 , 44 ( 31 ): 16944 - 16955 .

Ramaswamy N , Gu W B , Ziegelbauer J M , et al . Carbon support microstructure impact on high current density transport resistances in PEMFC cathode [J ] . Journal of the Electrochemical Society , 2020 , 167 ( 6 ): 064515 .

Huo S , Jiao K , Park J W . On the water transport behavior and phase transition mechanisms in cold start operation of PEM fuel cell [J ] . Applied Energy , 2019 , 233 : 776 - 788 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Optimization of ternary-distillation sequence based on gradient boosting decision tree

Multi-objective optimization design of ammonia decomposition catalysts by coupling with interpretable machine learning and genetic algorithm

ANN-GA integrated framework for intelligent screening of ORC mixture working fluids and performance optimization

Research on the CO2 adsorption performance and mechanism of hierarchically amine-modified MOF-74

From waste PET to high-value chemicals: advances in catalytic oxidation upcycling

Related Author

LIU Shanghao

JIA Shengkun

LUO Yiqing

YUAN Xigang

LIU Shanghao

JIA Shengkun

LUO Yiqing

YUAN Xigang

Related Institution

School of Chemical Engineering and Technology, Tianjin University

Chemical Engineering Research Center, Tianjin University

State Key Laboratory of Chemical Engineering, Tianjin University

School of Chemical Engineering and Technology， Tianjin University

Chemical Engineering Research Center，Tianjin University

⁰