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

doi:10.19799/j.cnki.2095-4239.2024.0627

储能科学与技术 ›› 2024, Vol. 13 ›› Issue (9): 3059-3071.doi: 10.19799/j.cnki.2095-4239.2024.0627

• AI辅助先进电池设计与应用专刊 • 上一篇

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

柯学¹(), 洪华伟², 郑鹏³, 李智诚⁴, 范培潇¹, 杨军¹, 郭宇铮¹, 蒯春光¹()

^1.武汉大学电气与自动化学院，湖北武汉 430072
^2.国家电网福建省电力有限公司营销服务中心，福建福州 350001
^3.国家电网福建省电力有限公司，福建福州 350001
^4.国家电网福建省电力有限公司电力科学研究院，福建福州 350007

收稿日期:2024-07-08 修回日期:2024-08-03 出版日期:2024-09-28 发布日期:2024-09-20
通讯作者: 蒯春光 E-mail:whumas_ke@163.com;chunguangk@whu.edu.cn
作者简介:柯学（1993—），男，博士研究生，研究方向为锂离子电池健康状态诊断，E-mail：whumas_ke@163.com；
基金资助:
国家电网公司总部科技项目(5108-202218280A-2-148-XG)

Estimating lithium-ion battery health using automatic feature extraction and channel attention mechanisms for multi-timescale modeling

Xue KE¹(), Huawei HONG², Peng ZHENG³, Zhicheng LI⁴, Peixiao FAN¹, Jun YANG¹, Yuzheng GUO¹, Chunguang KUAI¹()

^1.School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, Hubei, China
^2.Marketing Service Center, State Grid Fujian Electric Power Company, Fuzhou 350001, Fujian, China
^3.State Grid Fujian Electric Power Company, Fuzhou 350001, Fujian, China
^4.Power Science Research Institute, State Grid Fujian Electric Power Company, Fuzhou 350007, Fujian, China

Received:2024-07-08 Revised:2024-08-03 Online:2024-09-28 Published:2024-09-20
Contact: Chunguang KUAI E-mail:whumas_ke@163.com;chunguangk@whu.edu.cn

摘要/Abstract

摘要：

准确估计锂离子电池(lithium-ion battery，LIB)的健康状态(state of health，SOH)对于确保储能电站的安全稳定运行至关重要。然而，现有的数据驱动方法通常依赖手工特征提取，并且特征的时间尺度比较单一，很难进行高效且精确的电池健康状态评估。为了解决这些问题，提出了一种基于多时间尺度建模自动特征提取和通道注意力机制的健康状态估计模型。该模型首先将充电过程信息输入多个并行的膨胀卷积模块(dilation convolution module，DCM)，从不同时间尺度进行自动特征提取，获得丰富且全面的特征表示。随后，不同尺度的特征通过融合后结合门控循环单元(gated recurrent unit，GRU)提取时间序列的长期依赖关系。模型进一步融入通道注意力机制(efficient channel attention，ECA)，对历史信息进行相关性动态权重分配，关注显著特征。最后，在两个公开数据集上验证了本方法的优越性，并与其他常用深度学习模型进行了比较。结果表明，本模型具有较高的SOH估计精度和良好的迁移性，两个数据集上的均方根误差分别仅为0.0110和0.0095，在跨数据集的迁移实验中均方误差仅为0.0092。

关键词: 锂离子电池, 健康状态, 卷积神经网络, 注意力机制, 时间序列

Abstract:

Accurate estimation of the state of health (SOH) in lithium-ion batteries (LIB) is crucial for the safe and stable operation of energy storage systems. Current data-driven approaches often rely on manual feature extraction or fall short in single-scale feature representation. To address these issues, this paper introduces a novel SOH estimation model that leverages automatic feature extraction and channel attention mechanisms for multi-timescale modeling. The approach begins with inputting charging process data into multiple parallel dilation convolution modules (DCM), which automatically extract features across various time scales, creating a rich and comprehensive feature representation. These multi-scale features are then integrated and processed by a gated recurrent unit (GRU) to capture long-term dependencies in the time series data. Furthermore, the model incorporates the efficient channel attention (ECA) mechanism, which dynamically adjusts the importance of historical information and emphasizes critical features. The proposed method's effectiveness is validated through experiments two public datasets, showcasing a significant improvement over common deep learning models. Results demonstrate that the model proposed in this study exhibits high precision in SOH estimation and robust transferability. The model achieves low Root Mean Square Errors (RMSE) of 0.0110 and 0.0095 on these datasets, respectively, and maintains an RMSE of only 0.0092 in cross-dataset transfer experiments. These findings underscore the efficacy and adaptability of the proposed model in executing SOH predictions across different datasets.

Key words: lithium-ion battery, state of health, convolutional neural network, attention mechanism, time series

中图分类号:

TM 912

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.

Xue KE, Huawei HONG, Peng ZHENG, Zhicheng LI, Peixiao FAN, Jun YANG, Yuzheng GUO, Chunguang KUAI. Estimating lithium-ion battery health using automatic feature extraction and channel attention mechanisms for multi-timescale modeling[J]. Energy Storage Science and Technology, 2024, 13(9): 3059-3071.

图/表 12

图1

图2

图3

图4

图5

图6

图7

图8

表1

图9

表2

图10

参考文献 32

1	XU J, MEI X S, WANG X, et al. A relative state of health estimation method based on wavelet analysis for lithium-ion battery cells[J]. IEEE Transactions on Industrial Electronics, 2021, 68(8): 6973-6981. DOI: 10.1109/TIE.2020.3001836.
2	ROUHOLAMINI M, WANG C S, NEHRIR H, et al. A review of modeling, management, and applications of grid-connected Li-ion battery storage systems[J]. IEEE Transactions on Smart Grid, 2022, 13(6): 4505-4524. DOI: 10.1109/TSG.2022.3188598.
3	熊庆, 邸振国, 汲胜昌, 锂离子电池健康状态估计及寿命预测研究进展综述[J], 高电压技术, 2024, 50(3): 1182-1195. DOI: 10.13336/j.1003-6520.hve.20221843.
	XIONG Q, DI Z G, JI S C, Review on health state estimation and life prediction of lithium-ion batteries[J], High Voltage Engineering, 2024, 50(3): 1182-1195. DOI: 10.13336/j.1003-6520.hve.20221843.
4	BAO Z Y, JIANG J H, ZHU C X, et al. A new hybrid neural network method for state-of-health estimation of lithium-ion battery[J]. Energies, 2022, 15(12): 4399. DOI: 10.3390/en15124399.
5	高仁璟, 吕治强, 赵帅, 等. 基于电化学模型的锂离子电池健康状态估算[J]. 北京理工大学学报, 2022, 42(8): 791-797. DOI: 10.15918/j.tbit1001-0645.2021.310.
	GAO R J, LYU Z Q, ZHAO S, et al. Health state estimation of Li-ion batteries based on electrochemical model[J]. Transactions of Beijing Institute of Technology, 2022, 42(8): 791-797. DOI: 10. 15918/j.tbit1001-0645.2021.310.
6	颜湘武, 邓浩然, 郭琪, 等. 基于自适应无迹卡尔曼滤波的动力电池健康状态检测及梯次利用研究[J]. 电工技术学报, 2019, 34(18): 3937-3948. DOI: 10.19595/j.cnki.1000-6753.tces.171452.
	YAN X W, DENG H R, GUO Q, et al. Study on the state of health detection of power batteries based on adaptive unscented Kalman filters and the battery echelon utilization[J]. Transactions of China Electrotechnical Society, 2019, 34(18): 3937-3948. DOI: 10.19595/j.cnki.1000-6753.tces.171452.
7	LI C, ZHANG H H, DING P, et al. Deep feature extraction in lifetime prognostics of lithium-ion batteries: Advances, challenges and perspectives[J]. Renewable and Sustainable Energy Reviews, 2023, 184: 113576. DOI: 10.1016/j.rser.2023.113576.
8	戴彦文, 于艾清. 基于健康特征参数的CNN-LSTM&GRU组合锂电池SOH估计[J]. 储能科学与技术, 2022, 11(5): 1641-1649.
	DAI Y W, YU A Q. Combined CNN-LSTM and GRU based health feature parameters for lithium-ion batteries SOH estimation[J]. Energy Storage Science and Technology, 2022, 11(5): 1641-1649.
9	LI X Y, YUAN C G, LI X H, et al. State of health estimation for Li-ion battery using incremental capacity analysis and Gaussian process regression[J]. Energy, 2020, 190: 116467. DOI: 10.1016/j.energy.2019.116467.
10	王琛, 闵永军. 基于容量增量曲线与GWO-GPR的锂离子电池SOH估计[J]. 储能科学与技术, 2023, 12(11): 3508-3518.
	WANG C, MIN Y J. SOH estimation of lithium-ion batteries based on capacity increment curve and GWO-GPR[J]. Energy Storage Science and Technology, 2023, 12(11): 3508-3518.
11	JIA J F, YUAN S F, SHI Y H, et al. Improved sparrow search algorithm optimization deep extreme learning machine for lithium-ion battery state-of-health prediction[J]. iScience, 2022, 25(4): 103988. DOI: 10.1016/j.isci.2022.103988.
12	ZHU J G, WANG Y X, HUANG Y, et al. Data-driven capacity estimation of commercial lithium-ion batteries from voltage relaxation[J]. Nature Communications, 2022, 13(1): 2261. DOI: 10.1038/s41467-022-29837-w.
13	LIN M Q, WU D G, MENG J H, et al. A multi-feature-based multi-model fusion method for state of health estimation of lithium-ion batteries[J]. Journal of Power Sources, 2022, 518, 230774. DOI: 10.1016/j.jpowsour.2021.230774.
14	BAO Z Y, NIE J H, LIN H P, et al. A global-local context embedding learning based sequence-free framework for state of health estimation of lithium-ion battery[J]. Energy, 2023, 282: 128306. DOI: 10.1016/j.energy.2023.128306.
15	JIANG Y Y, CHEN Y, YANG F F, et al. State of health estimation of lithium-ion battery with automatic feature extraction and self-attention learning mechanism[J]. Journal of Power Sources, 2023, 556: 232466. DOI: 10.1016/j.jpowsour.2022.232466.
16	李超然, 肖飞, 樊亚翔, 等. 基于卷积神经网络的锂离子电池SOH估算[J]. 电工技术学报, 2020, 35(19): 4106-4119. DOI: 10.19595/j.cnki.1000-6753.tces.191617.
	LI C R, XIAO F, FAN Y X, et al. An approach to lithium-ion battery SOH estimation based on convolutional neural network[J]. Transactions of China Electrotechnical Society, 2020, 35(19): 4106-4119. DOI: 10.19595/j.cnki.1000-6753.tces.191617.
17	FU P Y, CHU L, LI J H, et al. State of health prediction of lithium-ion battery based on deep dilated convolution[J]. Sensors, 2022, 22(23): 9435. DOI: 10.3390/s22239435.
18	SUN S, SUN J Z, WANG Z L, et al. Prediction of battery SOH by CNN-BiLSTM network fused with attention mechanism[J]. Energies, 2022, 15(12): 4428. DOI: 10.3390/en15124428.
19	LI L, LI Y J, MAO R Z, et al. Remaining useful life prediction for lithium-ion batteries with a hybrid model based on TCN-GRU-DNN and dual attention mechanism[J]. IEEE Transactions on Transportation Electrification, 2023, 9(3): 4726-4740. DOI: 10.1109/TTE.2023.3247614.
20	毛百海, 覃吴, 肖显斌, 等. 基于LSTM&GRU-Attention多联合模型的锂离子电池SOH估计[J]. 储能科学与技术, 2023, 12(11): 3519-3527.
	MAO B H, QIN W, XIAO X B, et al. SOH estimation of lithium-ion batteries based on LSTM & GRU-attention multijoint model[J]. Energy Storage Science and Technology, 2023, 12(11): 3519-3527.
21	LIN M Q, WU J, MENG J H, et al. State of health estimation with attentional long short-term memory network for lithium-ion batteries[J]. Energy, 2023, 268: 126706. DOI: 10.1016/j.energy. 2023.126706.
22	SAHA B, GOEBEL K. Battery data set[DB]. NASA AMES prognostics data repository, 2007.
23	XING Y J, MA E W M, TSUI K L, et al. An ensemble model for predicting the remaining useful performance of lithium-ion batteries[J]. Microelectronics Reliability, 2013, 53(6): 811-820. DOI: 10.1016/j.microrel.2012.12.003.
24	LIU B L, XU J L, XIA W. State-of-health estimation for lithium-ion battery based on an attention-based CNN-GRU model with reconstructed feature series[J]. International Journal of Energy Research, 2023, 2023: 8569161. DOI: 10.1155/2023/8569161.
25	YU F, KOLTUN V. Multi-scale context aggregation by dilated convolutions[EB/OL]. 2015: 1511. 07122.[2024-02-03]. https://arxiv.org/abs/1511.07122v3
26	WANG F J, ZHAI Z, LIU B C, et al. Open access dataset, code library and benchmarking deep learning approaches for state-of-health estimation of lithium-ion batteries[J]. Journal of Energy Storage, 2024, 77: 109884. DOI: 10.1016/j.est.2023.109884.
27	WANG Q L, WU B G, ZHU P F, et al. ECA-net: Efficient channel attention for deep convolutional neural networks[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020: 11531-11539. DOI: 10.1109/CVPR42600. 2020.01155.
28	HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[DB/OL]. 2017[2023-01-05]. https://doi.org/10.48550/arXiv.1709.01507.
29	FU S Y, TAO S Y, FAN H T, et al. Data-driven capacity estimation for lithium-ion batteries with feature matching based transfer learning method[J]. Applied Energy, 2024, 353: 121991. DOI: 10.1016/j.apenergy.2023.121991.
30	RUAN H K, WEI Z B, SHANG W T, et al. Artificial Intelligence-based health diagnostic of lithium-ion battery leveraging transient stage of constant current and constant voltage charging[J]. Applied Energy, 2023, 336: 120751. DOI: 10.1016/j.apenergy. 2023.120751.
31	PAN R, LIU T S, HUANG W, et al. State of health estimation for lithium-ion batteries based on two-stage features extraction and gradient boosting decision tree[J]. Energy, 2023, 285: 129460. DOI: 10.1016/j.energy.2023.129460.
32	WANG F J, ZHAO Z B, ZHAI Z, et al. Explainability-driven model improvement for SOH estimation of lithium-ion battery[J]. Reliability Engineering & System Safety, 2023, 232: 109046. DOI: 10.1016/j.ress.2022.109046.

方法	B05		B06		B07		B18		平均值
方法	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE
CNN	0.0314	0.0326	0.0266	0.0326	0.0169	0.0184	0.0171	0.0195	0.0230	0.0258
GRU	0.0183	0.0193	0.0284	0.0311	0.0116	0.0129	0.0187	0.0217	0.0192	0.0212
文献[31]	0.0080	0.0092	0.0111	0.0209	0.0105	0.0118	0.0094	0.0104	0.0097	0.0131
文献[30]	0.0109	—	0.0117	—	0.0154	—	0.0169	—	0.0137	—
DGE	0.0141	0.0152	0.0201	0.0235	0.0091	0.0107	0.0116	0.0144	0.0137	0.0160
MDGE	0.0058	0.0082	0.0134	0.0173	0.0063	0.0073	0.0096	0.0113	0.0088	0.0110

方法	CS2_35		CS2_36		CS2_37		CS2_38		平均值
方法	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE
CNN	0.0219	0.0229	0.0328	0.0346	0.0257	0.0261	0.0272	0.0302	0.0269	0.0284
GRU	0.0080	0.0110	0.0164	0.0181	0.0135	0.0152	0.0186	0.0221	0.0141	0.0166
文献[31]	0.0118	0.0184	0.0142	0.0229	0.0104	0.0117	0.0107	0.0162	0.0118	0.0173
文献[32]	0.0135	0.0146	0.0237	0.0263	0.0164	0.0182	0.0746	0.0900	0.0320	0.0373
DGE	0.0074	0.0097	0.0116	0.0139	0.0084	0.0108	0.0116	0.0152	0.0097	0.0124
MDGE	0.0055	0.0077	0.0067	0.0096	0.0062	0.0079	0.0092	0.0131	0.0069	0.0095
T1-MDGE	0.0093	0.0106	0.0095	0.0112	0.0091	0.0102	0.0109	0.0145	0.0097	0.0116
T2-MDGE	0.0050	0.0069	0.0068	0.0099	0.0055	0.0073	0.0097	0.0126	0.0068	0.0092

[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]	胡雪峰, 常先雷, 刘肖肖, 徐威, 张文彬. 适用于宽温度范围的锂离子电池SOC估计方法[J]. 储能科学与技术, 2024, 13(9): 2983-2994.
[3]	陈媛, 章思源, 蔡宇晶, 黄小贺, 刘炎忠. 融合多项式特征扩展与CNN-Transformer模型的锂电池SOH估计[J]. 储能科学与技术, 2024, 13(9): 2995-3005.
[4]	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.
[5]	何宁, 杨芳芳. 考虑能量和温度特征的锂离子电池早期寿命预测[J]. 储能科学与技术, 2024, 13(9): 3016-3029.
[6]	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.
[7]	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.
[8]	孙丙香, 杨鑫, 周兴振, 马仕昌, 王志豪, 张维戈. 基于简化阻抗模型和比较元启发式算法的锂离子电池参数辨识方法[J]. 储能科学与技术, 2024, 13(9): 2952-2962.
[9]	黄煜峰, 梁焕超, 许磊. 基于卡尔曼滤波算法优化Transformer模型的锂离子电池健康状态预测方法[J]. 储能科学与技术, 2024, 13(8): 2791-2802.
[10]	王志勇, 蔡君瑶, 佘英奇, 钟树林, 潘康华. 氮杂环导电高分子改性锂离子电池石墨负极材料[J]. 储能科学与技术, 2024, 13(8): 2511-2518.
[11]	雷晶晶, 李泽皓, 陈斌斌, 黄登高. 基于电化学阻抗谱的电芯内部温度估计研究[J]. 储能科学与技术, 2024, 13(8): 2823-2834.
[12]	陈悦林, 马宏忠, 朱沐雨, 宣文婧, 王思涵. 磷酸铁锂电池组在电网调峰工况下的液冷技术研究[J]. 储能科学与技术, 2024, 13(8): 2704-2712.
[13]	何忆南, 张锴, 周俊武, 王欣杨, 郑百林. 外部载荷对硅电极锂电池循环性能的影响[J]. 储能科学与技术, 2024, 13(8): 2559-2569.
[14]	巩文豪, 李蒙, 张涛, 张若涛, 刘艳侠. 高能量长续航无人机电池的开发及制备[J]. 储能科学与技术, 2024, 13(8): 2550-2558.
[15]	陈国贺, 吕培召, 李孟涵, 饶中浩. 锂离子电池热失控传播特性及其抑制策略研究进展[J]. 储能科学与技术, 2024, 13(7): 2470-2482.

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

Estimating lithium-ion battery health using automatic feature extraction and channel attention mechanisms for multi-timescale modeling

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 32

相关文章 15

编辑推荐

Metrics

本文评价