In consideration of the characteristics of the thermal management system for proton exchange membrane fuel cell （PEMFC）, including nonlinearity, strong coupling, and significant time delay, this study proposes a BP neural network PID control method （BP-PID） optimized by the bald eagle search algorithm （BES）. This approach addresses the problenis of the conventional BP-PID method, such as slow learning rate and susceptibility to local optima, thereby enabling rapid adjustment of the fuel cell under varying operating conditions and reducing temperature fluctuations. A comparative analysis of four control methods—fuzzy PID, BP-PID, PSO-BP-PID, and BES-BP-PID—reveals the superior performance of the proposed BES-BP-PID method. Specifically, compared to BP-PID, BES-BP-PID reduces overshoot by 15.6% and decreases settling time by 29 seconds. Furthermore, when benchmarked against PSO-BP-PID, it achieves a lower root mean square error （RMSE） and smoother temperature transients.
Key words
proton exchange membrane fuel cell /
thermal management /
temperature control /
baldeagle search algorithm /
neural network
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1] 王洪建, 王冬冬, 曹权, 等. 燃料电池分布式供能技术发展现状及分析[J]. 中国电机工程学报, 2024, 44(20): 8113-8125.
Wang H J, Wang D D, CAO Q, et al.Development status and analysis of fuel cell based distributed energy supply technology[J]. Proceedings of the CSEE, 2024, 44(20): 8113-8125.
[2] Liso V, Nielsen M P, Ker S K, et al.Thermal modeling and temperature control of a PEM fuel cell system for forklift applications[J]. International Journal of Hydrogen Energy, 2014, 39(16): 8410-8420.
[3] 彭书浩. 质子交换膜燃料电池热管理系统控制策略研究[D]. 杭州: 浙江大学, 2022.
Peng S H.Research of control strategy on thermal management system of proton exchange membrane fuel cell[D]. Hangzhou: Zhejiang University, 2022.
[4] 陈际, 袁守利, 刘志恩. 基于BAS改进PSO算法对PEMFC温度的控制[J]. 太阳能学报, 2023, 44(5): 67-73.
Chen J, Yuan S L, Liu Z E.Temperature control of PEMFC based on BAS improved PSO algorithm[J]. Acta Energiae Solaris Sinica, 2023, 44(5): 67-73.
[5] 赵洪波, 刘杰, 马彪, 等. 水冷PEMFC热管理系统控制策略及仿真研究[J]. 化工学报, 2020, 71(5): 2139-2150.
Zhao H B, Liu J, Ma B, et al.Control strategy and simulation research of water-cooled PEMFC thermal management system[J]. CIESC Journal, 2020, 71(5): 2139-2150.
[6] 杨何, 赵津, 刘照, 等. 应用APSO改进BP-PID的PEMFC热管理系统温度控制研究[J]. 重庆理工大学学报(自然科学), 2023, 37(9): 332-339.
Yang H, Zhao J, Liu Z, et al.Temperature control study of PEMFC thermal management system using APSO to improve BP-PID[J]. Journal of Chongqing University of Technology (Natural Science), 2023, 37(9): 332-339.
[7] 赵洪山, 潘思潮, 吴雨晨, 等. 基于深度确定性策略梯度的PEMFC的水泵和散热器联合控制研究[J]. 太阳能学报, 2024, 45(6): 92-101.
Zhao H S, Pan S C, Wu Y C, et al.Study on joint control of pump and radiator in PEMFC based on deep deterministic policy gradient[J]. Acta Energiae Solaris Sinica, 2024, 45(6): 92-101.
[8] 孙明, 邹浓茂, 白阳振, 等. PEMFC热管理系统的改进偏差型自抗扰控制[J]. 太阳能学报, 2024, 45(10): 68-76.
SUN M, ZOU N M, BAI Y Z, et al.Improved error-based active disturbance rejection control for thermal management system of PEMFC[J]. Acta Energiae Solaris Sinica, 2024, 45(10): 68-76.
[9] Wang Y, Ruiz Diaz D F, Chen K S, et al. Materials, technological status, and fundamentals of PEM fuel cells-A review[J]. Materials Today, 2020, 32: 178-203.
[10] 汪圣祥. 基于BP神经网络的PID研究和改进[D]. 广州: 广东工业大学, 2017.
Wang S X.Research and improvement of PID based on BP neural network[D]. Guangzhou: Guangdong University of Technology, 2017.
[11] Alsattar H A, Zaidan A A, Zaidan B B.Novel meta-heuristic bald eagle search optimisation algorithm[J]. Artificial Intelligence Review, 2020, 53(3): 2237-2264.
PDF(1439 KB)
