 Optimization of fuel cell shutdown purge strategy based on machine learning: Mechanism analysis and experimental verificationLei Shi, Chang Du, Julong Zhou, Yahui Yi, Ruitao Li, Ze Liu, Jianbin Su, Liqin Qian, Tiancai Ma and Xingwang Tang Renewable Energy, 2025, vol. 248, issue C Abstract: Shutdown purging can significantly enhance the cold start success rate of fuel cells while mitigating mechanical degradation. This study first identifies that the temperature, relative pressure, relative humidity, and flow rate of the purge gas, within the ranges of 333.15–353.15 K, 20–90 %, 20–90 %, and 0.1–2 Q, respectively, have a notable impact on the purging effectiveness. Subsequently, the PSO-SVR-NSGA-II algorithm is employed to optimize these variables, yielding optimal purging conditions of 333.17 K, 20.013 %, 20.027 %, and 1.0355 Q for temperature, relative pressure, relative humidity, and purge flow rate, respectively. Finally, purging experiments demonstrate that under the same purging duration, the optimized conditions increase the HFR value by 0.79 mΩ, confirming the effectiveness of the optimization strategy. This study provides a new reference for the development of shutdown purging optimization strategies for fuel cells. Keywords: Shutdown purge; Machine learning; Purge gas parameters; NSGA-II; Purge experiment (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:eee:renene:v:248:y:2025:i:c:s0960148125008274 DOI: 10.1016/j.renene.2025.123165 Access Statistics for this article Renewable Energy is currently edited by Soteris A. Kalogirou and Paul Christodoulides More articles in Renewable Energy from Elsevier |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.