基于条件神经网络的质子交换膜燃料电池的老化性能预测

doi:10.19799/j.cnki.2095-4239.2024.0287

摘要/Abstract

摘要：

在积极推进“双碳”目标的背景下，氢能的发展迎来了前所未有的机遇。作为绿色交通变革的重要一环，燃料电池汽车在减碳和实现碳中和方面发挥着关键作用，同时也成为新能源汽车研究的焦点。提高燃料电池汽车的智能化程度，通过机器学习算法不断优化性能，已成为解决燃料电池汽车问题的重要途径。质子交换膜燃料电池作为燃料电池的核心技术之一，其耐用性问题依然是制约其商业化和市场普及的主要障碍。鉴于燃料电池的非线性和动态特性，以及运行条件的不断变化，准确预测其老化性能极具挑战。本工作提出一种基于条件卷积神经网络的新型燃料电池老化性能预测模型。该模型结合线性趋势和非线性动态特征预测，通过递归方法迭代预测燃料电池的老化性能。实验结果验证了本模型在长期性能预测上的高准确性，对于增强燃料电池系统的可靠性和效率具有重要的实际意义。

关键词: 燃料电池, 机器学习, 神经网络, 时间序列预测

Abstract:

In the context of actively pursuing the "dual carbon" goals, the advancement of hydrogen energy has experienced unprecedented opportunities. As a vital component of the green transportation revolution, fuel cell vehicles play a key role in carbon reduction and achieving carbon neutrality. Such vehicles have also become a focus of research on new energy vehicles. Improving the intelligence of fuel cell vehicles and continuously optimizing their performance through machine learning algorithms have become important ways to enhance the efficiency of such vehicles. Proton exchange membrane fuel cells, one of the core technologies of fuel cells, continue to encounter significant challenges in commercialization and market adoption due to durability issues. Accurately predicting the aging performance of fuel cells is highly challenging due to their nonlinearity and dynamic characteristics, coupled with their ever-changing operating conditions. This paper proposes a novel fuel cell performance prediction model based on conditional convolutional neural networks. The proposed model combines linear trends and nonlinear dynamic feature predictions to iteratively forecast the aging performance of fuel cells using a recursive method. The experimental results confirmed the high accuracy of this model in long-term performance prediction, instilling confidence in its practical implications for enhancing the reliability and efficiency of fuel cell systems.

Key words: fuel cell, machine learning, neural network, time series forecasting

中图分类号:

U 469.72

李从心, 岳美玲, 李昕彤, 熊庆辉, 刘孝艳. 基于条件神经网络的质子交换膜燃料电池的老化性能预测[J]. 储能科学与技术, 2024, 13(9): 3094-3102.

Congxin LI, Meiling YUE, Xintong LI, Qinghui XIONG, Xiaoyan LIU. Proton exchange membrane fuel cell aging performance prediction based on conditional neural networks[J]. Energy Storage Science and Technology, 2024, 13(9): 3094-3102.

图/表 12

图1

图2

图 3

表1

图4

表2

图5

表3

图6

表4

图7

图8

参考文献 20

1	黄沙, 李亚新. 基于计算机软件的燃料电池混合储能系统分析[J]. 储能科学与技术, 2024, 13(4): 1350-1352. DOI: 10.19799/j.cnki. 2095-4239.2024.0281.
	HUANG S, LI Y X. Analysis of fuel cell hybrid energy storage system based on computer software[J]. Energy Storage Science and Technology, 2024, 13(4): 1350-1352. DOI: 10.19799/j.cnki. 2095-4239.2024.0281.
2	李奇, 刘嘉蔚, 陈维荣. 质子交换膜燃料电池剩余使用寿命预测方法综述及展望[J]. 中国电机工程学报, 2019, 39(8): 2365-2375. DOI: 10.13334/j.0258-8013.pcsee.181308.
	LI Q, LIU J W, CHEN W R. Review and prospect of remaining useful life prediction methods for proton exchange membrane fuel cell[J]. Proceedings of the CSEE, 2019, 39(8): 2365-2375. DOI: 10.13334/j.0258-8013.pcsee.181308.
3	BRESSEL M, HILAIRET M, HISSEL D, et al. Remaining useful life prediction and uncertainty quantification of proton exchange membrane fuel cell under variable load[J]. IEEE Transactions on Industrial Electronics, 2016, 63(4): 2569-2577. DOI: 10.1109/TIE.2016.2519328.
4	JOUIN M, GOURIVEAU R, HISSEL D, et al. Joint particle filters prognostics for proton exchange membrane fuel cell power prediction at constant current solicitation[J]. IEEE Transactions on Reliability, 2016, 65(1): 336-349. DOI: 10.1109/TR.2015. 2454499.
5	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. DOI: 10.3969/j.issn.0258-2724.20180016.
	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. DOI: 10.3969/j.issn.0258-2724.20180016.
6	HE W B, LIU T, MING W Y, et al. Progress in prediction of remaining useful life of hydrogen fuel cells based on deep learning[J]. Renewable and Sustainable Energy Reviews, 2024, 192: 114193. DOI: 10.1016/j.rser.2023.114193.
7	ZHOU D M, AL-DURRA A, ZHANG K, et al. Online remaining useful lifetime prediction of proton exchange membrane fuel cells using a novel robust methodology[J]. Journal of Power Sources, 2018, 399: 314-328. DOI: 10.1016/j.jpowsour.2018.06.098.
8	MORANDO S, JEMEI S, HISSEL D, et al. Proton exchange membrane fuel cell ageing forecasting algorithm based on Echo State Network[J]. International Journal of Hydrogen Energy, 2017, 42(2): 1472-1480. DOI: 10.1016/j.ijhydene.2016.05.286.
9	MA R, YANG T, BREAZ E, et al. Data-driven proton exchange membrane fuel cell degradation predication through deep learning method[J]. Applied Energy, 2018, 231: 102-115. DOI: 10.1016/j.apenergy.2018.09.111.
10	曾其权, 罗马吉, 杨印龙, 等. 基于LSTM-UPF混合驱动方法的燃料电池寿命预测[J]. 储能科学与技术, 2024, 13(3): 963-970. DOI: 10.19799/j.cnki.2095-4239.2023.0705.
	ZENG Q Q, LUO M J, YANG Y L, et al. Life prediction of fuel cells based on the LSTM-UPF hybrid method[J]. Energy Storage Science and Technology, 2024, 13(3): 963-970. DOI: 10.19799/j.cnki.2095-4239.2023.0705.
11	ZHANG Z D, WANG Y X, HE H W, et al. A short- and long-term prognostic associating with remaining useful life estimation for proton exchange membrane fuel cell[J]. Applied Energy, 2021, 304: 117841. DOI: 10.1016/j.apenergy.2021.117841.
12	WANG C, LI Z L, OUTBIB R, et al. A novel long short-term memory networks-based data-driven prognostic strategy for proton exchange membrane fuel cells[J]. International Journal of Hydrogen Energy, 2022, 47(18): 10395-10408. DOI: 10.1016/j.ijhydene.2022.01.121.
13	MA T C, ZHANG Z L, LIN W K, et al. Impedance prediction model based on convolutional neural networks methodology for proton exchange membrane fuel cell[J]. International Journal of Hydrogen Energy, 2021, 46(35): 18534-18545. DOI: 10.1016/j.ijhydene.2021.02.204.
14	HUO W W, LI W E, ZHANG Z H, et al. Performance prediction of proton-exchange membrane fuel cell based on convolutional neural network and random forest feature selection[J]. Energy Conversion and Management, 2021, 243: 114367. DOI: 10.1016/j.enconman.2021.114367.
15	LIU F F, GAO Z L, SU J Z, et al. Understanding the process of carbon corrosion and its impact on performance degradation during simulated start-stop operations for the proton exchange membrane fuel cell[J]. Electrochimica Acta, 2023, 468: 143193. DOI: 10.1016/j.electacta.2023.143193.
16	PAN M Z, PAN C J, LI C, et al. A review of membranes in proton exchange membrane fuel cells: Transport phenomena, performance and durability[J]. Renewable and Sustainable Energy Reviews, 2021, 141: 110771. DOI: 10.1016/j.rser.2021. 110771.
17	姚颖方, 刘建国, 邹志刚. 燃料电池膜电极衰减机制及其抗老化策略[J]. 电化学, 2018, 24(6): 664-676. DOI: 10.13208/j.electrochem. 180853.
	YAO Y F, LIU J G, ZOU Z G. Degradation mechanism and anti-aging strategies of membrane electrode assembly of fuel cells[J]. Journal of Electrochemistry, 2018, 24(6): 664-676. DOI: 10. 13208/j.electrochem.180853.
18	YUAN H, DAI H F, MING P W, et al. Understanding dynamic behavior of proton exchange membrane fuel cell in the view of internal dynamics based on impedance[J]. Chemical Engineering Journal, 2022, 431: 134035. DOI: 10.1016/j.cej.2021.134035.
19	BENAGGOUNE K, YUE M L, JEMEI S, et al. A data-driven method for multi-step-ahead prediction and long-term prognostics of proton exchange membrane fuel cell[J]. Applied Energy, 2022, 313: 118835. DOI: 10.1016/j.apenergy.2022.118835.
20	YUE M L, ZHANG X, TENG T, et al. Trend-focused dynamic degradation prediction based on echo state networks in automotive fuel cells[J]. Energy Science & Engineering, 2024, 12(4): 1462-1471. DOI: 10.1002/ese3.1669.

参数	值
活化面积	33.625 cm²
单电池个数	15
氢气压力	35 kPa
工作温度	75 ℃
最大电流	13.45 A(0.4 A/cm²)

超参数	值
输入层维度	64
卷积层数量	3
卷积核大小	5
卷积和数量	10
池化层大小	2
全连接层神经元数量	128
激活函数	ReLU
优化器	Adam
学习率	0.001
批大小(batch size)	128
训练轮数(epochs)	1000

预测值	RMSE	MAPE
P₇₀₀	0.1013	0.8524
P₁₀₀₀	0.0772	0.6792

预测值	RMSE	MAPE
P₇₀₀	0.2014	1.7213
P₈₀₀	0.1947	1.7201
P₉₀₀	0.1812	1.6624
P₁₀₀₀	0.1729	1.5210

[1]	陆继忠, 彭思敏, 李晓宇. 基于多特征量分析和LSTM-XGBoost模型的锂离子电池SOH估计方法[J]. 储能科学与技术, 2024, 13(9): 2972-2982.
[2]	李亚捷, 王依平, 陈斌, 林海龙, 张更, 施思齐. 机器学习辅助相场模拟预测锂离子输运参数对电池枝晶最大生长高度和空间利用率的影响[J]. 储能科学与技术, 2024, 13(9): 2864-2870.
[3]	邢瑞鹤, 翁素婷, 李叶晶, 张佳怡, 张浩, 王雪锋. AI辅助电池材料表征与数据分析[J]. 储能科学与技术, 2024, 13(9): 2839-2863.
[4]	管鸿盛, 钱诚, 孙博, 任羿. 贫数据条件下锂离子电池容量退化轨迹预测方法[J]. 储能科学与技术, 2024, 13(9): 3084-3093.
[5]	刘定宏, 董文楷, 李召阳, 张红烛, 齐昕. 基于RUN-GRU-attention模型的实车动力电池健康状态估计方法[J]. 储能科学与技术, 2024, 13(9): 3042-3058.
[6]	柯学, 洪华伟, 郑鹏, 李智诚, 范培潇, 杨军, 郭宇铮, 蒯春光. 基于多时间尺度建模自动特征提取和通道注意力机制的锂离子电池健康状态估计[J]. 储能科学与技术, 2024, 13(9): 3059-3071.
[7]	刘子玉, 姜泽坤, 邱伟, 徐泉, 牛迎春, 徐春明, 周天航. 人工智能在长时液流电池储能中的应用：性能优化和大模型[J]. 储能科学与技术, 2024, 13(9): 2871-2883.
[8]	邓斌, 华海明, 张与之, 王晓旭, 张林峰. 深度势能方法及其在电化学储能材料中的应用[J]. 储能科学与技术, 2024, 13(9): 2884-2906.
[9]	何智峰, 陶远哲, 胡泳钢, 王其聪, 杨勇. 机器学习强化的电化学阻抗谱技术及其在锂离子电池研究中的应用[J]. 储能科学与技术, 2024, 13(9): 2933-2951.
[10]	李畅, 郑伟波, 朱帅, 姜云文, 明平文. 基于模型的燃料电池空气子系统动态过程研究[J]. 储能科学与技术, 2024, 13(8): 2580-2588.
[11]	白颖. 低温燃料电池在物流运输系统中的供能作用研究[J]. 储能科学与技术, 2024, 13(7): 2459-2461.
[12]	李淼, 盖克荣, 周凤颖, 黄欢, 杨永强. 低温燃料电池在汽车工程中的供储能特性分析[J]. 储能科学与技术, 2024, 13(7): 2483-2485.
[13]	刘偲艳, 钟根香, 葛庆. 基于FDC氢燃料电池堆在线智能监测系统[J]. 储能科学与技术, 2024, 13(6): 2030-2038.
[14]	唐梓巍, 师玉璞, 张雨禅, 周奕博, 杜慧玲. 基于Informer神经网络的锂离子电池容量退化轨迹预测[J]. 储能科学与技术, 2024, 13(5): 1658-1666.
[15]	张忠豪, 邱殿凯, 彭林法, 易培云. 一体式再生燃料电池双功能氧电极高分散工艺研究[J]. 储能科学与技术, 2024, 13(5): 1417-1426.