质子交换膜燃料电池冷启动堆栈温度预测模型

doi:10.11949/0438-1157.20221149

摘要/Abstract

摘要：

为了快速准确地预测出质子交换膜燃料电池(proton exchange membrane fuel cell，PEMFC)在冷启动过程中的启动时长及启动方法的应用效果，提出了以堆栈温度和温度增量分别作为BP(back propagation)神经网络预测目标的堆栈温度实时预测模型，分别为模型T和模型K，并采用四个不同的预测精度评估标准来评估预测结果的准确性。基于文献中三种冷启动工况实验数据对预测模型进行验证，结果表明，模型K的平均相对误差在三种工况下均低于模型T，分别为0.4553、0.9537和1.0844。模型T在早期预测阶段缺乏训练样本，预测结果的堆栈温度变化趋势为零，因而模型K在早期预测阶段具有更大优势。堆栈温度变化趋势预测方法能够为用户当前的PEMFC冷启动实现效果提供参考。

关键词: 燃料电池, 预测, 神经网络, 冷启动, 堆栈温度

Abstract:

In order to quickly and accurately predict the start-up duration of a proton exchange membrane fuel cell (PEMFC) during the cold-start process and the application effect of the start-up method, two real-time prediction models of the stack temperature change trend are proposed. The two prediction models take the stack temperature and the temperature increment as the prediction targets of the BP neural network, named model T and model K, respectively. Meanwhile, four different prediction accuracy evaluation criteria are used to evaluate the accuracy of the prediction results. The prediction model is verified based on the experimental data of three cold-start conditions in the literature. The results show that the average relative error of model K is lower than that of model T under the three cold-start conditions, which are 0.4553, 0.9537, and 1.0844, respectively. Model T lacks training samples in the early prediction stage, and the stack temperature variation trend of the prediction results is zero, so model K has a greater advantage in the early prediction stage. The stack temperature change trend prediction method can provide a reference for the user’s current PEMFC cold-start implementation effect.

Key words: fuel cell, prediction, neural network, cold-start, stack temperature

中图分类号:

TM 911.4

张慧颖, 蔡伟华, 高明, 王宇航, 何锁盈. 质子交换膜燃料电池冷启动堆栈温度预测模型[J]. 化工学报, 2022, 73(11): 5056-5064.

Huiying ZHANG, Weihua CAI, Ming GAO, Yuhang WANG, Suoying HE. Cold-start stack temperature prediction model for proton exchange membrane fuel cells[J]. CIESC Journal, 2022, 73(11): 5056-5064.

图/表 12

图1 基于BP神经网络的实时PEMFC冷启动预测框架

Fig.1 Real-time PEMFC cold-start prediction framework based on BP neural network

图2 PEMFC冷启动实验测试平台

Fig.2 PEMFC cold-start experimental test platform

图3 PEMFC堆栈结构和温度测量的位置

Fig.3 The structure of the PEMFC stack and the locations of measuring temperature

图4 PEMFC冷启动实验数据

Fig.4 PEMFC cold-start experimental data

图5 低温环境PEMFC堆栈温度预测流程

Fig.5 PEMFC stack temperature prediction process in low temperature environment

图6 不同隐含层神经元个数的模型误差

Fig.6 Model errors with different numbers of neurons in the hidden layer

图7 工况1冷启动堆栈温度预测结果

Fig.7 The cold-start stack temperature prediction results taking the cold-start method 1 as a sample

图8 工况2冷启动堆栈温度预测结果

Fig.8 The cold-start stack temperature prediction results taking the cold-start method 2 as a sample

图9 工况3冷启动堆栈温度预测结果

Fig.9 The cold-start stack temperature prediction results taking the cold-start method 3 as a sample

图10 不同工况实时堆栈温度预测结果评估

Fig. 10 Evaluation of real-time stack temperature prediction results in different cold-start methods

图11 模型T和K的实时堆栈温度变化趋势预测结果误差

Fig.11 Errors in prediction results of real-time stack temperature trends for models T and K

表1 实时PEMFC堆栈温度变化趋势预测结果评估

Table 1 Evaluation of real-time PEMFC stack temperature trend prediction results

冷启动预测工况	预测模型	MRD	MSE	RMSE	R²
1	T	0.8431	10.4632	3.2347	0.9237
	K	0.4553	2.6385	1.6243	0.9808
2	T	1.4804	11.4387	3.3821	0.9052
	K	0.9537	6.4051	2.5308	0.9469
3	T	1.1509	9.1069	3.0178	0.9147
	K	1.0844	17.2858	4.1576	0.8382

参考文献 32

1	徐斌. 基于改进差分进化算法的质子交换膜燃料电池模型参数优化识别[J]. 化工学报, 2021, 72(3): 1512-1520.
	Xu B. Parameter optimal identification of proton exchange membrane fuel cell model based on an improved differential evolution algorithm[J]. CIESC Journal, 2021, 72(3): 1512-1520.
2	邱玥, 周苏洋, 顾伟, 等. “碳达峰、碳中和”目标下混氢天然气技术应用前景分析[J]. 中国电机工程学报, 2022, 42(4): 1301-1321.
	Qiu Y, Zhou S Y, Gu W, et al. Application prospect analysis of hydrogen enriched compressed natural gas technologies under the target of carbon emission peak and carbon neutrality[J]. Proceedings of the CSEE, 2022, 42(4): 1301-1321.
3	刘应都, 郭红霞, 欧阳晓平. 氢燃料电池技术发展现状及未来展望[J]. 中国工程科学, 2021, 23(4): 162-171.
	Liu Y D, Guo H X, Ouyang X P. Development status and future prospects of hydrogen fuel cell technology[J]. Strategic Study of CAE, 2021, 23(4): 162-171.
4	Pahon E, Bouquain D, Hissel D, et al. Performance analysis of proton exchange membrane fuel cell in automotive applications[J]. Journal of Power Sources, 2021, 510: 230385.
5	Sürer M G, Arat H T. Advancements and current technologies on hydrogen fuel cell applications for marine vehicles[J]. International Journal of Hydrogen Energy, 2022, 47(45): 19865-19875.
6	Zhu Y K, Lin R, Han L H, et al. Investigation on cold start of polymer electrolyte membrane fuel cells stacks with diverse cathode flow fields[J]. International Journal of Hydrogen Energy, 2021, 46(7): 5580-5592.
7	Luo Y, Wu Y H, Li B, et al. Development and application of fuel cells in the automobile industry[J]. Journal of Energy Storage, 2021, 42: 103124.
8	季玮琛, 林瑞. 质子交换膜燃料电池冷启动研究及策略优化现状[J]. 科学通报, 2022, 67(19): 2241-2257.
	Ji W C, Lin R. Strategy optimization of proton exchange membrane fuel cell cold start[J]. Chinese Science Bulletin, 2022, 67(19): 2241-2257.
9	Luo Y Q, Jiao K. Cold start of proton exchange membrane fuel cell[J]. Progress in Energy and Combustion Science, 2018, 64: 29-61.
10	Lin R, Zhong D, Lan S B, et al. Experimental validation for enhancement of PEMFC cold start performance: based on the optimization of micro porous layer[J]. Applied Energy, 2021, 300: 117306.
11	Lin R, Zhu Y K, Ni M, et al. Consistency analysis of polymer electrolyte membrane fuel cell stack during cold start[J]. Applied Energy, 2019, 241: 420-432.
12	Yang Z R, Jiao K, Wu K C, et al. Numerical investigations of assisted heating cold start strategies for proton exchange membrane fuel cell systems[J]. Energy, 2021, 222: 119910.
13	Li Q H, Liu Z Q, Sun Y, et al. A review on temperature control of proton exchange membrane fuel cells[J]. Processes, 2021, 9(2): 235.
14	Luo M Z, Zhang J, Zhang C Z, et al. Cold start investigation of fuel cell vehicles with coolant preheating strategy[J]. Applied Thermal Engineering, 2022, 201: 117816.
15	Sun J Q, Yang X K, Sun S C, et al. Investigation on the temperature uniformity and efficiency of cold start-up for proton exchange membrane fuel cell stack based on catalytic hydrogen/oxygen method[J]. Journal of Power Sources, 2021, 496: 229755.
16	Zhong D, Lin R, Jiang Z H, et al. Low temperature durability and consistency analysis of proton exchange membrane fuel cell stack based on comprehensive characterizations[J]. Applied Energy, 2020, 264: 114626.
17	林瑞, 蒋正华, 任应时, 等. 低温工况下燃料电池性能衰减及策略优化[J]. 同济大学学报(自然科学版), 2018, 46(5): 658-666.
	Lin R, Jiang Z H, Ren Y S, et al. Performance degradation and strategy optimization of PEMFCs under sub-freezing temperature[J]. Journal of Tongji University (Natural Science), 2018, 46(5): 658-666.
18	宇高义郎, 许竞莹, 王国卓, 等. 质子交换膜燃料电池内含水气体扩散层的冻结特性研究[J]. 化工学报, 2021, 72(4): 2276-2282.
	Utaka Y, Xu J Y, Wang G Z, et al. Study on freezing characteristics of water in gas diffusion layer of proton exchange membrane fuel cells[J]. CIESC Journal, 2021, 72(4): 2276-2282.
19	魏琳, 廖梓豪, 蒋方明. PEMFC冷却剂循环条件下冷启动数值模拟[J]. 化工学报, 2019, 70(S2): 146-154.
	Wei L, Liao Z H, Jiang F M. Numerical study on cold start of PEMFC with coolant circulation[J]. CIESC Journal, 2019, 70(S2): 146-154.
20	张雪霞, 高雨璇, 陈维荣. 基于数据驱动的质子交换膜燃料电池寿命预测[J]. 西南交通大学学报, 2020, 55(2): 417-427.
	Zhang X X, Gao Y X, Chen W R. Data-driven based remaining useful life prediction for proton exchange membrane fuel cells[J]. Journal of Southwest Jiaotong University, 2020, 55(2): 417-427.
21	Liu H, Chen J, Hissel D, et al. Short-term prognostics of PEM fuel cells: a comparative and improvement study[J]. IEEE Transactions on Industrial Electronics, 2019, 66(8): 6077-6086.
22	冯能莲,赵倩倩,雍加望.基于非线性动态模型的质子交换膜燃料电池故障诊断[J].化工学报, 2022, 73(9): 3983-3993.
	Feng N L, Zhao Q Q, Yong J W. Model-based fault diagnosis method for proton exchange membrane fuel cell system[J]. CIESC Journal, 2022, 73(9): 3983-3993.
23	Aubry J, Steiner N Y, Morando S, et al. Fuel cell diagnosis methods for embedded automotive applications[J]. Energy Reports, 2022, 8: 6687-6706.
24	Wang X C, Chen J Z, Quan S W, et al. Hierarchical model predictive control via deep learning vehicle speed predictions for oxygen stoichiometry regulation of fuel cells[J]. Applied Energy, 2020, 276: 115460.
25	Desantes J M, Novella R, Pla B, et al. A modeling framework for predicting the effect of the operating conditions and component sizing on fuel cell degradation and performance for automotive applications[J]. Applied Energy, 2022, 317: 119137.
26	杨秋香. 人工神经网络法在PEMFC性能研究中的应用[J]. 电源技术, 2018, 42(9): 1341-1344.
	Yang Q X. Application of artificial neural network to proton exchange membrane fuel cell performance research[J]. Chinese Journal of Power Sources, 2018, 42(9): 1341-1344.
27	Feng S S, Huang W T, Huang Z, et al. Optimization of maximum power density output for proton exchange membrane fuel cell based on a data-driven surrogate model[J]. Applied Energy, 2022, 317: 119158.
28	Musharavati F. Four dimensional bio-inspired optimization approach with artificial intelligence for proton exchange membrane fuel cell[J]. International Journal of Energy Research, DOI:10.1002/er.8007 .
29	Zhang C W, Chen S R, Gao H B, et al. State of charge estimation of power battery using improved back propagation neural network[J]. Batteries, 2018, 4(4): 69.
30	颜建国, 郑书闽, 郭鹏程, 等. 基于GA-BP神经网络的超临界CO₂传热特性预测研究[J]. 化工学报, 2021, 72(9): 4649-4657.
	Yan J G, Zheng S M, Guo P C, et al. Prediction of heat transfer characteristics for supercritical CO₂ based on GA-BP neural network[J]. CIESC Journal, 2021, 72(9): 4649-4657.
31	胡兵, 王小娟, 徐立军, 等. 基于KMO-PCA-BP的燃料电池堆输出电压预测方法[J]. 太阳能学报, 2022, 43(3): 12-19.
	Hu B, Wang X J, Xu L J, et al. Output voltage prediction method of fuel cell stack based on KMO-PCA-BP[J]. Acta Energiae Solaris Sinica, 2022, 43(3): 12-19.
32	李继清, 王爽, 段志鹏, 等. 基于ESMD-BP神经网络组合模型的中长期径流预报[J]. 应用基础与工程科学学报, 2020, 28(4): 817-832.
	Li J Q, Wang S, Duan Z P, et al. Medium and long-term runoff forecast based on ESMD-BP neural network combined model[J]. Journal of Basic Science and Engineering, 2020, 28(4): 817-832.

[1]	李艺彤, 郭航, 陈浩, 叶芳. 催化剂非均匀分布的质子交换膜燃料电池操作条件研究[J]. 化工学报, 2023, 74(9): 3831-3840.
[2]	温凯杰, 郭力, 夏诏杰, 陈建华. 一种耦合CFD与深度学习的气固快速模拟方法[J]. 化工学报, 2023, 74(9): 3775-3785.
[3]	陈哲文, 魏俊杰, 张玉明. 超临界水煤气化耦合SOFC发电系统集成及其能量转化机制[J]. 化工学报, 2023, 74(9): 3888-3902.
[4]	尹刚, 李伊惠, 何飞, 曹文琦, 王民, 颜非亚, 向禹, 卢剑, 罗斌, 卢润廷. 基于KPCA和SVM的铝电解槽漏槽事故预警方法[J]. 化工学报, 2023, 74(8): 3419-3428.
[5]	诸程瑛, 王振雷. 基于改进深度强化学习的乙烯裂解炉操作优化[J]. 化工学报, 2023, 74(8): 3429-3437.
[6]	闫琳琦, 王振雷. 基于STA-BiLSTM-LightGBM组合模型的多步预测软测量建模[J]. 化工学报, 2023, 74(8): 3407-3418.
[7]	徐野, 黄文君, 米俊芃, 申川川, 金建祥. 多源信息融合的离心式压缩机喘振诊断方法[J]. 化工学报, 2023, 74(7): 2979-2987.
[8]	郭雨莹, 敬加强, 黄婉妮, 张平, 孙杰, 朱宇, 冯君炫, 陆洪江. 稠油管道水润滑减阻及压降预测模型修正[J]. 化工学报, 2023, 74(7): 2898-2907.
[9]	李艳辉, 丁邵明, 白周央, 张一楠, 于智红, 邢利梅, 高鹏飞, 王永贞. 非常规服役超临界锅炉的微纳尺度腐蚀动力学模型建立及应用[J]. 化工学报, 2023, 74(6): 2436-2446.
[10]	于源, 陈薇薇, 付俊杰, 刘家祥, 焦志伟. 几何相似涡流空气分级机环形区流场变化规律研究及预测[J]. 化工学报, 2023, 74(6): 2363-2373.
[11]	高学金, 姚玉卓, 韩华云, 齐咏生. 基于注意力动态卷积自编码器的发酵过程故障监测[J]. 化工学报, 2023, 74(6): 2503-2521.
[12]	黄磊, 孔令学, 白进, 李怀柱, 郭振兴, 白宗庆, 李平, 李文. 油页岩添加对准东高钠煤灰熔融行为影响的研究[J]. 化工学报, 2023, 74(5): 2123-2135.
[13]	贠程, 王倩琳, 陈锋, 张鑫, 窦站, 颜廷俊. 基于社团结构的化工过程风险演化路径深度挖掘[J]. 化工学报, 2023, 74(4): 1639-1650.
[14]	罗来明, 张劲, 郭志斌, 王海宁, 卢善富, 相艳. 1~5 kW高温聚合物电解质膜燃料电池堆的理论模拟与组装测试[J]. 化工学报, 2023, 74(4): 1724-1734.
[15]	吴心远, 刘奇磊, 曹博渊, 张磊, 都健. Group2vec：基于无监督机器学习的基团向量表示及其物性预测应用[J]. 化工学报, 2023, 74(3): 1187-1194.