{"title":"考虑膜降解的质子交换膜燃料电池动态耦合特性分析及多约束优化","authors":"Kui Xu, Liyun Fan, Chen Chen, Chongchong Shen, Zejun Jiang, Yunpeng Wei","doi":"10.1016/j.fuel.2025.136275","DOIUrl":null,"url":null,"abstract":"<div><div>The performance degradation of the Proton Exchange Membrane Fuel Cell (PEMFC) system under variable loads is a key issue that restricts the application reliability and economy. This study develops an integrated “thermodynamics − economy” multi-physics coupling framework that quantifies cross-scale interactions among thermal, electrical, gas, and liquid. To resolve the limitations of conventional electrical models, a multi physics field dynamic model is established, revealing dynamic coupling characteristics between operational parameters (load current, temperature, anode humidification) and system performance indicators (membrane water content, system net power, electro-thermal efficiency, operational costs). A multi constraint optimization framework combining Convolutional Neural Network (CNN) and Multi Objective Particle Swarm Optimization (MOPSO) is proposed to achieve Pareto-optimal solutions for thermodynamic performance (8.91 % net power enhancement) and economic targets (3.63 % cost reduction) under multiple constraints. The CNN component extracts high-dimensional feature correlations from multi-physics simulations, while the MOPSO ensures global search efficiency. Furthermore, a physics-informed membrane degradation model is developed by embedding conductivity decay mechanisms into the multi-physics framework, enabling quantitative comparison of degradation trajectories before/after optimization. The results show that the proposed framework significantly slows membrane degradation (the attenuation of conductivity during 991 h operation was optimized by 10.26 %) through parameter threshold regulation. Finally, the effectiveness of the multi constraint optimization strategy and consideration of membrane degradation in improving the overall performance of the PEMFC system were discussed. This work establishes critical theoretical boundaries for the PEMFC control strategies and provides a data-mechanism fusion methodology for durability system design, demonstrating potential for next-generation long-life fuel cell technologies.</div></div>","PeriodicalId":325,"journal":{"name":"Fuel","volume":"404 ","pages":"Article 136275"},"PeriodicalIF":7.5000,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Analysis of dynamic coupling characteristics and multi-constraint optimization of a proton exchange membrane fuel cell considering membrane degradation\",\"authors\":\"Kui Xu, Liyun Fan, Chen Chen, Chongchong Shen, Zejun Jiang, Yunpeng Wei\",\"doi\":\"10.1016/j.fuel.2025.136275\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>The performance degradation of the Proton Exchange Membrane Fuel Cell (PEMFC) system under variable loads is a key issue that restricts the application reliability and economy. This study develops an integrated “thermodynamics − economy” multi-physics coupling framework that quantifies cross-scale interactions among thermal, electrical, gas, and liquid. To resolve the limitations of conventional electrical models, a multi physics field dynamic model is established, revealing dynamic coupling characteristics between operational parameters (load current, temperature, anode humidification) and system performance indicators (membrane water content, system net power, electro-thermal efficiency, operational costs). A multi constraint optimization framework combining Convolutional Neural Network (CNN) and Multi Objective Particle Swarm Optimization (MOPSO) is proposed to achieve Pareto-optimal solutions for thermodynamic performance (8.91 % net power enhancement) and economic targets (3.63 % cost reduction) under multiple constraints. The CNN component extracts high-dimensional feature correlations from multi-physics simulations, while the MOPSO ensures global search efficiency. Furthermore, a physics-informed membrane degradation model is developed by embedding conductivity decay mechanisms into the multi-physics framework, enabling quantitative comparison of degradation trajectories before/after optimization. The results show that the proposed framework significantly slows membrane degradation (the attenuation of conductivity during 991 h operation was optimized by 10.26 %) through parameter threshold regulation. Finally, the effectiveness of the multi constraint optimization strategy and consideration of membrane degradation in improving the overall performance of the PEMFC system were discussed. This work establishes critical theoretical boundaries for the PEMFC control strategies and provides a data-mechanism fusion methodology for durability system design, demonstrating potential for next-generation long-life fuel cell technologies.</div></div>\",\"PeriodicalId\":325,\"journal\":{\"name\":\"Fuel\",\"volume\":\"404 \",\"pages\":\"Article 136275\"},\"PeriodicalIF\":7.5000,\"publicationDate\":\"2025-07-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Fuel\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0016236125020009\",\"RegionNum\":1,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENERGY & FUELS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fuel","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0016236125020009","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
Analysis of dynamic coupling characteristics and multi-constraint optimization of a proton exchange membrane fuel cell considering membrane degradation
The performance degradation of the Proton Exchange Membrane Fuel Cell (PEMFC) system under variable loads is a key issue that restricts the application reliability and economy. This study develops an integrated “thermodynamics − economy” multi-physics coupling framework that quantifies cross-scale interactions among thermal, electrical, gas, and liquid. To resolve the limitations of conventional electrical models, a multi physics field dynamic model is established, revealing dynamic coupling characteristics between operational parameters (load current, temperature, anode humidification) and system performance indicators (membrane water content, system net power, electro-thermal efficiency, operational costs). A multi constraint optimization framework combining Convolutional Neural Network (CNN) and Multi Objective Particle Swarm Optimization (MOPSO) is proposed to achieve Pareto-optimal solutions for thermodynamic performance (8.91 % net power enhancement) and economic targets (3.63 % cost reduction) under multiple constraints. The CNN component extracts high-dimensional feature correlations from multi-physics simulations, while the MOPSO ensures global search efficiency. Furthermore, a physics-informed membrane degradation model is developed by embedding conductivity decay mechanisms into the multi-physics framework, enabling quantitative comparison of degradation trajectories before/after optimization. The results show that the proposed framework significantly slows membrane degradation (the attenuation of conductivity during 991 h operation was optimized by 10.26 %) through parameter threshold regulation. Finally, the effectiveness of the multi constraint optimization strategy and consideration of membrane degradation in improving the overall performance of the PEMFC system were discussed. This work establishes critical theoretical boundaries for the PEMFC control strategies and provides a data-mechanism fusion methodology for durability system design, demonstrating potential for next-generation long-life fuel cell technologies.
期刊介绍:
The exploration of energy sources remains a critical matter of study. For the past nine decades, fuel has consistently held the forefront in primary research efforts within the field of energy science. This area of investigation encompasses a wide range of subjects, with a particular emphasis on emerging concerns like environmental factors and pollution.