Performance optimization of a baffle straight-channel proton exchange membrane fuel cell based on a BO-XGBoost ensemble surrogate model
Main Article Content
Abstract
A three-dimensional, steady-state and isothermal model of a baffle straight-channel proton exchange membrane fuel cell (PEMFC) is established to investigate the effects of baffle height, width and position on cathode oxygen distribution, water removal and current density at 0.7 V. To overcome the limited robustness of a conventional artificial neural network under small-sample and strongly coupled design variables, a Bayesian-optimized XGBoost (BO-XGBoost) multi-output surrogate model is developed. The baffle geometric parameters are used as inputs, and the oxygen concentration difference, maximum water content at the GDL/channel interface and current density are used as outputs. Tree boosting, Bayesian hyperparameter search and cross-validation are combined to improve nonlinear prediction accuracy. The original CFD data are calibrated and expanded to a candidate design space of 13671 cases, while the final optimal solution is kept unchanged. The results show that the PEMFC obtains the best comprehensive performance when the baffle height, width and position are 0.95 mm, 0.35 mm and 3 mm, respectively.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
Y. Wang, K. S. Chen, J. Mishler, S. C. Cho, and X. C. Adroher, “A review of polymer electrolyte membrane fuel cells: Technology, applications, and needs on fundamental research,” Applied Energy, vol. 88, no. 4, pp. 981–1007, 2011.
M. Sauermoser, N. Kizilova, B. G. Pollet, and S. Kjelstrup, “Flow field patterns for proton exchange membrane fuel cells,” Frontiers in Energy Research, vol. 8, p. 13, 2020.
Y. Yin, X. Wang, X. Shangguan, et al., “Numerical investigation on the characteristics of mass transport and performance of PEMFC with baffle plates installed in the flow channel,” International Journal of Hydrogen Energy, vol. 43, no. 16, pp. 8048–8062, 2018.
Z. Qin, W. Huo, Z. Bao, et al., “Alternating flow field design improves the performance of proton exchange membrane fuel cells,” Advanced Science, vol. 10, p. 2206788, 2023.
F. Sun, D. Su, P. Li, and X. Dong, “A novel 3D fine-mesh flow field design and performance analysis for proton exchange membrane fuel cells,” Journal of Power Sources, vol. 584, p. 233572, 2023.
D. K. Dang and B. Zhou, “Enhanced water management in PEMFC cathode using streamlined baffles,” Journal of Power Sources, vol. 623, p. 235475, 2024.
M. Ghasabehi, S. Shakerinejad, A. Ramiar, et al., “Optimization of baffle and tapering integration in the cathode flow field of proton exchange membrane fuel cells,” Energy, vol. 293, p. 130663, 2024.
X. Zhou, J. Zhang, K. Feng, Z. Qiao, Y. Wang, and L. Shi, “Machine learning-assisted design of flow fields for proton exchange membrane fuel cells,” Journal of Power Sources, vol. 626, p. 235753, 2025.
K. Jiang, H. Jiang, Z. Liang, et al., “An automated, intelligent and efficient approach to design flow fields of proton exchange membrane fuel cells: A concept for future,” Chemical Engineering Journal, vol. 523, p. 168164, 2025.
T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785–794.
Mojica, F, Rahman, M. A, Mora, and J. M, “Experimental Study of Three Channel Designs with Model Comparison in a PEM Fuel Cell,” Fuel Cells, 2020.
J. J. Baschuk and X. Li, “A comprehensive, consistent and systematic mathematical model of PEM fuel cells,” Applied Energy, vol. 86, no. 2, pp. 181–193, 2009.
J. J. Baschuk and X. Li, “A general formulation for a mathematical PEM fuel cell model,” Journal of Power Sources, vol. 142, no. 1-2, pp. 134–153, 2005.