融合自注意力机制与门控循环单元网络的宽工况锂离子电池SOC估计

doi:10.19799/j.cnki.2095-4239.2023.0292

储能科学与技术 ›› 2023, Vol. 12 ›› Issue (7): 2229-2237.doi: 10.19799/j.cnki.2095-4239.2023.0292

• 储能锂离子电池系统关键技术专刊 • 上一篇下一篇

融合自注意力机制与门控循环单元网络的宽工况锂离子电池SOC估计

管鸿盛(), 钱诚(), 徐炳辉, 孙博, 任羿

北京航空航天大学可靠性与系统工程学院，北京 100191

收稿日期:2023-04-28 修回日期:2023-05-23 出版日期:2023-07-05 发布日期:2023-07-25
通讯作者: 钱诚 E-mail:guanhs@buaa.edu.cn;cqian@buaa.edu.cn
作者简介:管鸿盛（1997—），男，硕士研究生，研究方向为锂离子电池状态估计，E-mail：guanhs@buaa.edu.cn；
基金资助:
国家自然科学基金项目(52075028)

SAM-GRU-based fusion neural network for SOC estimation in lithium-ion batteries under a wide range of operating conditions

Hongsheng GUAN(), Cheng QIAN(), Binghui XU, Bo SUN, Yi REN

School of Reliability and Systems Engineering, Beihang University, Beijing 100191, China

Received:2023-04-28 Revised:2023-05-23 Online:2023-07-05 Published:2023-07-25
Contact: Cheng QIAN E-mail:guanhs@buaa.edu.cn;cqian@buaa.edu.cn

摘要/Abstract

摘要：

准确估计宽工况条件下的锂离子电池荷电状态(SOC)对于电动汽车的运行安全性和可靠性至关重要，是电池管理系统最重要的任务之一。本工作充分利用门控循环单元(GRU)神经网络短时处理能力与注意力机制(SAM)长时序特征提取能力，提出了一种融合SAM与GRU的神经网络模型学习锂离子电池可测参数(电压、电流)与其SOC的非线性映射关系，实现了高精度的SOC估计，从而解决锂离子电池SOC的长序列相关特征难以有效表征问题。通过北京公交动态应力测试(BBDST)数据的验证表明，与传统GRU网络相比，本文提出的SAM-GRU神经网络模型对于不同放电倍率、环境温度以及放电倍率-环境温度混合工况下工作的锂离子电池均取得了更准确的SOC估计，估计精度提升分别不小于26%、25%和11%。

关键词: 锂离子电池, 荷电状态, 自注意力机制, 门控循环单元神经网络

Abstract:

Accurate estimation of the state of charge (SOC) of lithium-ion batteries under a wide range of operating conditions is crucial for ensuring the operational safety and reliability of electric vehicles; therefore, estimating SOC is one of the most important tasks of battery management systems. In this study, a fusion neural network model combining Self-Attention Mechanism (SAM) and Gated Recurrent Unit (GRU) is proposed to capture the long-term nonlinear mapping relationship between the measurable parameters (voltage and current) and SOC of lithium-ion batteries. This SAM-GRU neural network model makes full use of the short-time processing capability of GRU and the long-time sequence feature-extraction capability of SAM. Additionally, this model simplifies the effective characterization of the long-sequence-related features of SOC. Based on the results of the Beijing Bus Dynamic Stress Test, the proposed SAM-GRU neural network model yields more accurate SOC estimates than the traditional GRU neural network under different discharge rates, environmental temperatures, and combinations of both. Specifically, the improvements in accuracy are no less than 26%, 25%, and 11%, respectively.

Key words: lithium-ion battery, state of charge, self-attentive mechanism, gated recurrent unit neural network

中图分类号:

TM 912

管鸿盛, 钱诚, 徐炳辉, 孙博, 任羿. 融合自注意力机制与门控循环单元网络的宽工况锂离子电池SOC估计[J]. 储能科学与技术, 2023, 12(7): 2229-2237.

Hongsheng GUAN, Cheng QIAN, Binghui XU, Bo SUN, Yi REN. SAM-GRU-based fusion neural network for SOC estimation in lithium-ion batteries under a wide range of operating conditions[J]. Energy Storage Science and Technology, 2023, 12(7): 2229-2237.

图/表 14

图1

图2

图3

表1

图4

表2

图5

图6

表3

图7

表 4

图8

表5

图9

参考文献 18

1	YANG C F, WANG X Y, FANG Q H, et al. An online SOC and capacity estimation method for aged lithium-ion battery pack considering cell inconsistency[J]. Journal of Energy Storage, 2020, 29: doi: 10.1016/j.est.2020.101250.
2	HOSSAIN LIPU M S, HANNAN M A, KARIM T F, et al. Intelligent algorithms and control strategies for battery management system in electric vehicles: Progress, challenges and future outlook[J]. Journal of Cleaner Production, 2021, 292: doi: 10.1016/j.jclepro. 2021.126044.
3	NI Z C, YANG Y. A combined data-model method for state-of-charge estimation of lithium-ion batteries[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-11.
4	WU L F, ZHANG Y. Attention-based encoder-decoder networks for state of charge estimation of lithium-ion battery[J]. Energy, 2023, 268: doi: 10.1016/j.energy.2023.126665.
5	BIAN C, YANG S K, LIU J, et al. Robust state-of-charge estimation of Li-ion batteries based on multichannel convolutional and bidirectional recurrent neural networks[J]. Applied Soft Computing, 2022, 116:doi: 10.1016/j.asoc.2021.108401.
6	GUO S S, MA L. A comparative study of different deep learning algorithms for lithium-ion batteries on state-of-charge estimation[J]. Energy, 2023, 263: doi: 10.1016/j.energy.2022.125872.
7	ZHANG G Y, XIA B Z, WANG J M. Intelligent state of charge estimation of lithium-ion batteries based on L-M optimized back-propagation neural network[J]. Journal of Energy Storage, 2021, 44: doi: 10.1016/j.est.2021.103442.
8	HOW D N T, HANNAN M A, HOSSAIN LIPU M S, et al. State-of-charge estimation of Li-ion battery in electric vehicles: A deep neural network approach[C]//2019 IEEE Industry Applications Society Annual Meeting. September 29—October 3, 2019, Baltimore, MD, USA. IEEE, 2019: 1-8.
9	HANNAN M A, HOW D N T, HOSSAIN LIPU M S, et al. SOC estimation of Li-ion batteries with learning rate-optimized deep fully convolutional network[J]. IEEE Transactions on Power Electronics, 2021, 36(7): 7349-7353.
10	LIU Y F, LI J Q, ZHANG G, et al. State of charge estimation of lithium-ion batteries based on temporal convolutional network and transfer learning[J]. IEEE Access, 2021, 9: 34177-34187.
11	CHEN J X, ZHANG Y, WU J, et al. SOC estimation for lithium-ion battery using the LSTM-RNN with extended input and constrained output[J]. Energy, 2023, 262: doi: 10.1016/j.energy.2022.125375.
12	TIAN J P, XIONG R, SHEN W X, et al. State-of-charge estimation of LiFePO₄ batteries in electric vehicles: A deep-learning enabled approach[J]. Applied Energy, 2021, 291:doi: 10.1016/j.apenergy. 2021.116812.
13	YANG F F, LI W H, LI C, et al. State-of-charge estimation of lithium-ion batteries based on gated recurrent neural network[J]. Energy, 2019, 175: 66-75.
14	HANNAN M A, HOW D N T, BIN MANSOR M, et al. State-of-charge estimation of Li-ion battery using gated recurrent unit with one-cycle learning rate policy[J]. IEEE Transactions on Industry Applications, 2021, 57(3): 2964-2971.
15	朱元富, 贺文武, 李建兴, 等. 基于Bi-LSTM/Bi-GRU循环神经网络的锂电池SOC估计[J]. 储能科学与技术, 2021, 10(3): 1163-1176.
	ZHU Y F, HE W W, LI J X, et al. SOC estimation for Li-ion batteries based on Bi-LSTM and Bi-GRU[J]. Energy Storage Science and Technology, 2021, 10(3): 1163-1176.
16	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]. La Jolla: Neural Information Processing Systems (nips), 2017: doi: 10.48550/arXiv.1706.03762.
17	HU C S, CHENG F J, MA L A, et al. State of charge estimation for lithium-ion batteries based on TCN-LSTM neural networks[J]. Journal of the Electrochemical Society, 2022, 169(3): 030544.
18	CHEN Z, ZHAO H Q, SHU X, et al. Synthetic state of charge estimation for lithium-ion batteries based on long short-term memory network modeling and adaptive H-Infinity filter[J]. Energy, 2021, 228: doi: 10.1016/j.energy.2021.120630.

网络层	特征数/隐藏节点数
输入	2
FC0	64
SAM层	64
GRU层	64
FC1	8
FC2(输出)	1

组号	电池编号	温度/℃	放电倍率
G1	B211、B212、B213	25	1 C
G2	B221、B222、B223	25	2 C
G3	B421、B422、B423	45	2 C

网络模型	1 C(B213)			2 C(B223)
网络模型	RMSE	MAE	MAX	RMSE	MAE	MAX
GRU	0.762	0.700	3.936	0.852	0.723	4.566
SAM-GRU	0.557	0.493	3.271	0.486	0.391	3.164

网络模型	25 ℃(B223)			45 ℃(B423)
网络模型	RMSE	MAE	MAX	RMSE	MAE	MAX
GRU	0.774	0.652	5.072	0.540	0.422	1.907
SAM-GRU	0.511	0.385	3.015	0.407	0.321	1.748

网络模型	1 C, 25 ℃(B213)			2 C, 25 ℃(B223)			2 C, 45 ℃(B423)
网络模型	RMSE	MAE	MAX	RMSE	MAE	MAX	RMSE	MAE	MAX
GRU	0.699	0.621	4.129	0.698	0.600	3.094	0.451	0.356	1.983
SAM-GRU	0.619	0.549	3.109	0.421	0.355	2.601	0.423	0.342	1.762

融合自注意力机制与门控循环单元网络的宽工况锂离子电池SOC估计

SAM-GRU-based fusion neural network for SOC estimation in lithium-ion batteries under a wide range of operating conditions

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 18

相关文章 15

编辑推荐

Metrics

本文评价

[1]	郝增辉, 刘训良, 孟缘, 孟楠, 温治. 电极界面微观结构对固态锂离子电池性能的影响[J]. 储能科学与技术, 2023, 12(7): 2095-2104.
[2]	刘书琴, 王小燕, 张振东, 段振霞. 锂离子电池组液冷式热管理系统的设计及优化[J]. 储能科学与技术, 2023, 12(7): 2155-2165.
[3]	张青松, 包防卫, 牛江昊. 环境压力对锂电池热失控产气及爆炸风险的影响[J]. 储能科学与技术, 2023, 12(7): 2263-2270.
[4]	陈智伟, 张维戈, 张珺玮, 张言茹. 基于视觉特征的动力电池组综合健康评估及分筛方法[J]. 储能科学与技术, 2023, 12(7): 2211-2219.
[5]	张宇波, 王有元, 黄洞宁, 王子懿, 陈伟根. 面向变工况条件的锂离子电池寿命退化预测方法[J]. 储能科学与技术, 2023, 12(7): 2238-2245.
[6]	徐冲, 徐宁, 蒋志敏, 李中凯, 胡洋, 严红, 马国强. 锂离子电池产气机制及基于电解液的抑制策略[J]. 储能科学与技术, 2023, 12(7): 2119-2133.
[7]	陈钦佩, 王学辉, 米文忠. 电动汽车锂离子电池系统热失控气体毒害及爆炸特性研究[J]. 储能科学与技术, 2023, 12(7): 2256-2262.
[8]	昝文达, 张睿, 丁飞. 锂离子电池电化学模型发展与应用[J]. 储能科学与技术, 2023, 12(7): 2302-2318.
[9]	吴宜琨, 何杰, 杨乐, 宋维力, 陈浩森. 锂离子电池多物理场多尺度变形理论模型与计算方法[J]. 储能科学与技术, 2023, 12(7): 2141-2154.
[10]	范茂松, 耿萌萌, 赵光金, 杨凯, 王放放, 刘皓. 基于多频点阻抗的梯次利用电池分选技术研究[J]. 储能科学与技术, 2023, 12(7): 2202-2210.
[11]	李晋, 王青松, 孔得朋, 王晓冬, 俞振华, 乐艳飞, 黄鑫炎, 胡振恺, 吴候福, 方华斌, 曹伟, 张少禹, 卓萍, 陈晔, 李紫婷, 梅文昕, 张越, 赵丽香, 唐亮, 黄宗侯, 陈篪, 刘彦辉, 储玉喜, 许晓元, 张晋, 李贻恺, 冯蓉, 杨标, 户波, 杨晓滢. 锂离子电池储能安全评价研究进展[J]. 储能科学与技术, 2023, 12(7): 2282-2301.
[12]	张佳怡, 翁素婷, 王兆翔, 王雪锋. 石墨负极界面SEI膜与锂离子电池热失控[J]. 储能科学与技术, 2023, 12(7): 2105-2118.
[13]	陈育新, 杨家沐, 练成, 刘洪来. 基于相场模型的锂电池电极浆料稳定涂布窗口分析[J]. 储能科学与技术, 2023, 12(7): 2185-2193.
[14]	杲齐新, 赵景腾, 李国兴. 锂离子电池快速充电研究进展[J]. 储能科学与技术, 2023, 12(7): 2166-2184.
[15]	李放, 闵永军, 张涌. 基于大数据的动力锂电池可靠性关键技术研究综述[J]. 储能科学与技术, 2023, 12(6): 1981-1994.