基于物理信息与深度神经网络的锂离子电池温度预测

doi:10.11930/j.issn.1004-9649.202403004

中国电力 ›› 2024, Vol. 57 ›› Issue (11): 18-25.DOI: 10.11930/j.issn.1004-9649.202403004

• 储能用锂离子电池本体安全关键技术 • 上一篇下一篇

基于物理信息与深度神经网络的锂离子电池温度预测

陈来恩¹(), 曾小勇¹(), 曾子豪², 成采辰¹, 孙耀科¹^,³

1. 长沙理工大学电气与信息工程学院，湖南长沙　410114
2. 国网湖南综合能源服务有限公司，湖南长沙　410000
3. 内华达大学拉斯维加斯分校，美国内华达州拉斯维加斯　89154

收稿日期:2024-03-01 出版日期:2024-11-28 发布日期:2024-11-27
作者简介:陈来恩（1999—），男，硕士研究生，从事锂离子电池建模及状态估计研究，E-mail：berrychen@stu.csust.edu.cn
曾小勇（1980—），男，通信作者，博士，讲师，从事非线性系统建模以及锂离子电池建模、状态估计研究，E-mail：super_zxy@163.com
基金资助:
国家自然科学基金资助项目（柔性直流输电交流侧故障下换流器多桥臂主动应对的能量调控机理及穿越控制研究，51977014）。

Temperature Prediction of Lithium-Ion Batteries Based on Physical Information and Deep Neural Network

Laien CHEN¹(), Xiaoyong ZENG¹(), Zihao ZENG², Caichen CHENG¹, Yaoke SUN¹^,³

1. School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410114, China
2. State Grid Hunan Comprehensive Energy Service Company Limited, Changsha 410000, China
3. University of Nevada, Las Vegas, Nevada Las Vegas 89154, The United States of America

Received:2024-03-01 Online:2024-11-28 Published:2024-11-27
Supported by:
This work is supported by National Natural Science Foundation of China (Research on Energy Regulation Mechanism and Faul Ride-through Control of Multi-armed Converter of AC Side Fault in MMC-HVDC System, No.51977014).

摘要/Abstract

摘要：

准确预测锂离子电池的温度是电池管理系统的关键技术。针对锂离子电池的动态以及时序依赖特性，构建了一种深度神经网络用于锂离子电池的温度预测。该模型可以提取数据的潜在高维特征并适当降维以减少模型复杂度，同时通过长短期记忆单元层捕获温度的长期依赖关系。此外，通过锂离子电池的开路电压、端电压以及电流实时计算产热率，从而为深度神经网络提供额外的物理信息输入。结果表明，该方法相比于其他方法具有更好的温度预测性能。

关键词: 锂离子电池, 温度预测, 产热率, 物理信息, 深度神经网络

Abstract:

Accurately predicting the temperature of lithium-ion batteries is a key technology for battery management systems. A deep neural network is constructed for temperature prediction of lithium-ion batteries based on their dynamic as well as time-dependent characteristics. The model can extract the potential high-dimension features of the data and appropriately reduce their dimensionality to reduce the model complexity while capturing the long-term dependence of temperature through the layer of long short-term memory cells. In addition, the heat generation rate is calculated in real-time through the open circuit voltage, terminal voltage and current of the lithium-ion battery, thus providing additional physical information input to the deep neural network. The results show that the method has better temperature prediction performance compared to other methods.

Key words: lithium-ion batteries, temperature prediction, heat generation rate, physical information, deep neural network.

陈来恩, 曾小勇, 曾子豪, 成采辰, 孙耀科. 基于物理信息与深度神经网络的锂离子电池温度预测[J]. 中国电力, 2024, 57(11): 18-25.

Laien CHEN, Xiaoyong ZENG, Zihao ZENG, Caichen CHENG, Yaoke SUN. Temperature Prediction of Lithium-Ion Batteries Based on Physical Information and Deep Neural Network[J]. Electric Power, 2024, 57(11): 18-25.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202403004

https://www.electricpower.com.cn/CN/Y2024/V57/I11/18

图/表 8

图 1 US06的电压、电流、SOC、温度曲线

Fig.1 Voltage, current, SOC, and temperature curves for US06

图 2 温度预测框架

Fig.2 The framework of temperature prediction

图 3 1 D卷积层的单元

Fig.3 The unit of 1 D convolution layer

图 4 LSTM单元结构

Fig.4 The structure of LSTM unit

图 5 4种不同驾驶驱动循环的结果

Fig.5 The result of four different driving cycles

表 1 4种驾驶驱动循环的误差指标

Table 1 Error indicators for four driving drive cycles

驾驶驱动循环	E_rms/℃	E_ma/℃	E_max/℃
HWFET	0.10	0.08	1.27
LA92	0.26	0.21	1.38
UDDS	0.14	0.10	1.27
US06	0.39	0.29	1.52

图 6 与不同方法的对比结果

Fig.6 Comparison with different methods

表 2 不同方法误差对比（HWFET）

Table 2 Errors of different methods (HWFET)

方法	E_rms/℃	E_ma/℃	E_max/℃
BP	0.79	0.54	3.62
GRU	0.18	0.14	1.21
DNN（无产热率）	0.13	0.10	1.61
DNN	0.10	0.08	1.27

参考文献 25

1	张媛, 夏向阳, 岳家辉, 等. 基于电池簇放电电量的电池堆不一致性在线监测方法[J]. 中国电力, 2023, 56 (7): 207- 215,227.
	ZHANG Yuan, XIA Xiangyang, YUE Jiahui, et al. Remaining useful life prediction and state of health estimation of lithium-Ion batteries based on voltage data segment hybrid model[J]. Electric Power, 2023, 56 (7): 207- 215,227.
2	刘周斌, 朱涛, 姜巍, 等. 储能锂离子电池包冷却系统的数值模拟与结构优化[J]. 中国电力, 2023, 56 (10): 202- 210.
	LIU Zhoubin, ZHU Tao, JIANG Wei, et al. Simulation analysis and structure optimization of cooling system for energy storage lithium-ion battery pack[J]. Electric Power, 2023, 56 (10): 202- 210.
3	WASEEM M, AHMAD M, PARVEEN A, et al. Battery technologies and functionality of battery management system for EVs: Current status, key challenges, and future prospectives[J]. Journal of Power Sources, 2023, 580, 233349. DOI
4	杜伟兮, 周子牛, 鲁金科, 等. 基于电化学阻抗谱的锂离子电池内部温度监测方法综述[J]. 广东电力, 2023, 36 (8): 27- 38.
	DU Weixi, ZHOU Ziniu, LU Jinke, et al. Review of internal temperature monitoring methods for lithium-ion batteries based on electrochemical impedance spectroscopy[J]. Guangdong Electric Power, 2023, 36 (8): 27- 38.
5	林甲深. 考虑温度影响的锂离子电池放电容量不确定度评定[J]. 电源技术, 2023, 47 (5): 635- 638. DOI
	LIN Jiashen. Uncertainty evaluation of discharge capacity of lithium ion battery considering temperature effect[J]. Chinese Journal of Power Sources, 2023, 47 (5): 635- 638. DOI
6	EL FALLAH S, KHARBACH J, HAMMOUCH Z, et al. State of charge estimation of an electric vehicle’s battery using Deep Neural Networks: Simulation and experimental results[J]. Journal of Energy Storage, 2023, 62, 106904. DOI
7	赵珈卉, 田立亭, 程林. 锂离子电池状态估计与剩余寿命预测方法综述[J]. 发电技术, 2023, 44 (1): 1- 17.
	ZHAO Jiahui, TIAN Liting, CHENG lin. Review on state estimation and remaining useful life prediction methods for lithium-ion battery[J]. Power Generation Technology, 2023, 44 (1): 1- 17.
8	黎冲, 王成辉, 王高, 等. 基于数据驱动的锂离子电池健康状态估计技术[J]. 中国电力, 2022, 55 (8): 73- 86, 95.
	LI Chong, WANG Chenghui, WANG Gao, et al. Technology of lithium-ion battery state-of-health assessment based on data-driven[J]. Electric Power, 2022, 55 (8): 73- 86, 95.
9	ZHENG Y S, CHE Y H, HU X S, et al. Thermal state monitoring of lithium-ion batteries: Progress, challenges, and opportunities[J]. Progress in Energy and Combustion Science, 2024, 100, 101120. DOI
10	周炜航, 叶青, 叶蕾, 等. 锂离子电池内温度场健康状态分布式光纤原位监测技术研究[J]. 中国激光, 2020, 47 (12): 154- 163.
	ZHOU Weihang, YE Qing, YE Lei, et al. Distributed optical fiber in situ monitoring technology for a healthy temperature field in lithium ion batteries[J]. Chinese Journal of Lasers, 2020, 47 (12): 154- 163.
11	范文杰, 徐广昊, 于泊宁, 等. 基于电化学阻抗谱的锂离子电池内部温度在线估计方法研究[J]. 中国电机工程学报, 2021, 41 (9): 3283- 3293.
	FAN Wenjie, XU Guanghao, YU Boning, et al. On-line estimation method for internal temperature of lithium-ion battery based on electrochemical impedance spectroscopy[J]. Proceedings of the CSEE, 2021, 41 (9): 3283- 3293.
12	熊瑞, 李幸港. 基于双卡尔曼滤波算法的动力电池内部温度估计[J]. 机械工程学报, 2020, 56 (14): 146- 151. DOI
	XIONG Rui, LI Xinggang. Battery internal temperature estimation method through double extended Kalman filtering algorithm[J]. Journal of Mechanical Engineering, 2020, 56 (14): 146- 151. DOI
13	谢家乐, 李增超, 王光, 等. 基于电热耦合效应的18650锂离子电池内外温度预测模型[J]. 机械工程学报, 2023, 59 (16): 342- 352. DOI
	XIE JiaLe, LI Zengchao, WANG Guang, et al. Internal and external temperature prediction models for 18650 li-ion battery based on electrical-thermal coupled effects[J]. Journal of Mechanical Engineering, 2023, 59 (16): 342- 352. DOI
14	FENG F, TENG S L, LIU K L, et al. Co-estimation of lithium-ion battery state of charge and state of temperature based on a hybrid electrochemical-thermal-neural-network model[J]. Journal of Power Sources, 2020, 455, 227935. DOI
15	HUSSEIN A A, CHEHADE A A. Robust artificial neural network-based models for accurate surface temperature estimation of batteries[J]. IEEE Transactions on Industry Applications, 2020, 56 (5): 5269- 5278. DOI
16	KLEINER J, STUCKENBERGER M, KOMSIYSKA L, et al. Real-time core temperature prediction of prismatic automotive lithium-ion battery cells based on artificial neural networks[J]. Journal of Energy Storage, 2021, 39, 102588. DOI
17	YAO Q, LU D D C, LEI G. A surface temperature estimation method for lithium-ion battery using enhanced GRU-RNN[J]. IEEE Transactions on Transportation Electrification, 2023, 9 (1): 1103- 1112. DOI
18	闫志远, 孙桓五, 刘世闯, 等. 一种基于GRU的氢燃料重卡汽车工况下锂离子电池温度预测模型[J]. 中国电机工程学报, 2024, 44 (6): 2330- 2339.
	YAN Zhiyuan, SUN Huanwu, LIU Shichuang, et al. A GRU based temperature prediction model of lithium-ion battery for hydrogen fuel heavy truck under operating conditions[J]. Proceedings of the CSEE, 2024, 44 (6): 2330- 2339.
19	ZHENG F D, XING Y J, JIANG J C, et al. Influence of different open circuit voltage tests on state of charge online estimation for lithium-ion batteries[J]. Applied Energy, 2016, 183, 513- 525. DOI
20	周飞燕, 金林鹏, 董军. 卷积神经网络研究综述[J]. 计算机学报, 2017, 40 (6): 1229- 1251. DOI
	ZHOU Feiyan, JIN Linpeng, DONG Jun. Review of convolutional neural network[J]. Chinese Journal of Computers, 2017, 40 (6): 1229- 1251. DOI
21	ZHU S, HE C N, ZHAO N Q, et al. Data-driven analysis on thermal effects and temperature changes of lithium-ion battery[J]. Journal of Power Sources, 2021, 482, 228983. DOI
22	杨丽, 吴雨茜, 王俊丽等. 循环神经网络研究综述[J]. 计算机应用, 2018, 38 (S2): 1- 6, 26.
	YANG Li, WU Yuqian, WANG Junli, et al. Research on recurrent neural network[J]. Journal of computer applications, 2018, 38 (S2): 1- 6, 26.
23	常禧龙, 梁琨, 李文涛. 深度学习优化器进展综述[J]. 计算机工程与应用, 2024, 60 (7): 1- 12. DOI
	CHANG Xilong, LIANG Kun, LI Wentao. Review of development of deep learning optimizer[J]. Computer Engineering and Applications, 2024, 60 (7): 1- 12. DOI
24	WEI J W, DONG G Z, CHEN Z H. Lyapunov-based thermal fault diagnosis of cylindrical lithium-ion batteries[J]. IEEE Transactions on Industrial Electronics, 2020, 67 (6): 4670- 4679. DOI
25	隋全武. 基于人工神经网络的锂离子电池组温度预测[J]. 小型内燃机与车辆技术, 2018, 47 (3): 71- 73. DOI
	SUI Quanwu. Temperature prediction of lithium-ion batteries based on artificial neural networks[J]. Small Internal Combustion Engine and Vehicle Technique, 2018, 47 (3): 71- 73. DOI

[1]	夏天, 刘代飞, 岳家辉, 陈来恩, 李亦梁. 基于蜣螂算法优化卡尔曼滤波的锂离子电池模型参数辨识[J]. 中国电力, 2025, 58(1): 196-204.
[2]	熊慧敏, 彭跃中, 何励学, 胡章茂, 王唯, 田红. 热管耦合相变材料全气候锂离子电池热管理系统性能分析[J]. 中国电力, 2024, 57(6): 27-36.
[3]	阎洁, 杨佳琳, 王航宇, 卢姣阳, 刘永前, 张磊. 基于风况预测误差自适应的海上风电场尾流偏转控制方法[J]. 中国电力, 2024, 57(3): 190-196.
[4]	夏向阳, 谭欣欣, 单周平, 李辉, 徐志强, 吴晋波, 岳家辉, 陈贵全. 储能电站锂离子电池本体安全关键技术及新技术应用情况[J]. 中国电力, 2024, 57(11): 1-17.
[5]	张媛, 夏向阳, 岳家辉, 刘代飞, 王明琦. 基于电池簇放电电量的电池堆不一致性在线监测方法[J]. 中国电力, 2023, 56(7): 207-215,227.
[6]	岳家辉, 夏向阳, 蒋戴宇, 周冠东, 徐志强, 张媛, 吕崇耿. 基于电压数据片段混合模型的锂离子电池剩余寿命预测与健康状态估计[J]. 中国电力, 2023, 56(7): 163-174.
[7]	刘文军, 欧名勇, 夏向阳, 李湘华, 岳家辉. 基于欧姆内阻压降的电池簇不一致性在线监测方法研究[J]. 中国电力, 2022, 55(8): 87-95.
[8]	黎冲, 王成辉, 王高, 鲁宗虎, 马成智. 基于数据驱动的锂离子电池健康状态估计技术[J]. 中国电力, 2022, 55(8): 73-86,95.
[9]	滕伟, 黄乙珂, 吴仕明, 柳亦兵. 基于XGBoost与LSTM的风力发电机绕组温度预测[J]. 中国电力, 2021, 54(6): 95-103.
[10]	孔雪卉, 张慧芬. 基于优化广义回归神经网络的变电站设备温度预测[J]. 中国电力, 2016, 49(7): 54-59.
[11]	苏伟, 钟国彬, 魏增福. 从正极材料看锂离子电池在储能领域的应用[J]. 中国电力, 2013, 46(8): 70-73.

基于物理信息与深度神经网络的锂离子电池温度预测

Temperature Prediction of Lithium-Ion Batteries Based on Physical Information and Deep Neural Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 25

相关文章 11

编辑推荐

Metrics

模态框（Modal）标题

基于物理信息与深度神经网络的锂离子电池温度预测

Temperature Prediction of Lithium-Ion Batteries Based on Physical Information and Deep Neural Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 25

相关文章 11

编辑推荐

Metrics