电池大数据智能分析平台的研发与应用

doi:10.19799/j.cnki.2095-4239.2024.0635

储能科学与技术 ›› 2024, Vol. 13 ›› Issue (9): 3198-3213.doi: 10.19799/j.cnki.2095-4239.2024.0635

• AI辅助先进电池设计与应用专刊 • 上一篇下一篇

电池大数据智能分析平台的研发与应用

焦君宇¹^,²^,³(), 张全權²(), 陈宁波², 王冀钰², 芦秋迪², 丁浩浩², 彭鹏³, 宋孝河³, 张帆³, 郑家新¹^,³()

^1.北京大学深圳研究生院，广东深圳 518052
^2.上海艮芯科技，上海 200135
^3.深圳屹艮科技，广东深圳 518052

收稿日期:2024-07-08 修回日期:2024-07-28 出版日期:2024-09-28 发布日期:2024-09-20
通讯作者: 郑家新 E-mail:jiaojunyu@eacomp.com;zhangquanquan@eacomp.com;zhengjx@pkusz.edu.cn
作者简介:焦君宇（1993—），男，博士，首席技术官，研究方向为电池大数据分析，E-mail：jiaojunyu@eacomp.com
张全權，男，硕士，算法工程师，研究方向为电池大数据分析，E-mail：zhangquanquan@eacomp.com；

Development and applications of an intelligent big data analysis platform for batteries

Junyu JIAO¹^,²^,³(), Quanquan ZHANG²(), Ningbo CHEN², Jiyu WANG², Qiudi LU², Haohao DING², Peng PENG³, Xiaohe SONG³, Fan ZHANG³, Jiaxin ZHENG¹^,³()

^1.Peking University Shenzhen Graduate School, Shenzhen 518052, Guangdong, China
^2.Shanghai Genthm Technology Co. , Ltd. , Shanghai 200135, China
^3.Shenzhen Eacomp Technology Co. , Ltd. , Shenzhen 518052, Guangdong, China

Received:2024-07-08 Revised:2024-07-28 Online:2024-09-28 Published:2024-09-20
Contact: Jiaxin ZHENG E-mail:jiaojunyu@eacomp.com;zhangquanquan@eacomp.com;zhengjx@pkusz.edu.cn

摘要/Abstract

摘要：

随着电动汽车和储能需求的持续增加，高性能电池的产量迅速上升，人们对电池先进制造的要求也越来越高。智能制造在电池行业中扮演着至关重要的角色，通过集成自动化技术、信息技术、计算仿真和人工智能，智能制造可以极大地提高生产效率和灵活性，减少人为错误，挖掘材料的内部机理，提高产品性能。基于人工智能的电池大数据分析技术是智能制造的重要一环，旨在通过高级数据分析技术，辅助研发人员开展各种电池的性能评估、预测与优化。为此，我们基于机器学习技术开发出一系列高效算法，实现电池大数据分析中的特征分析、电池一致性分析、电池健康状态估计以及电池剩余寿命预测等电池中常见的分析任务。此外，我们还提供了一个标准化的分析框架来全面分析电池数据、预测电池的性能，帮助研发人员直观理解复杂的数据集，并揭示数据中的模式和关系。同时，我们还将这些算法集成到电池大数据分析平台——智芯工坊中，以解决现有的电池大数据分析平台数据集成度低、分析工具单一和可扩展性不足等问题。这些智能算法的普及与应用有助于人们实现电池的高效分析与智能管理，进而推动电池行业的数智化发展。

关键词: 锂电池, 大数据, 人工智能, 软件平台, 特征, 电池剩余寿命, 电池健康状态

Abstract:

As the demand for electric vehicles and energy storage continues to grow, the production of high-performance batteries is increasing rapidly, leading to more stringent requirements for advanced manufacturing processes. Smart manufacturing is vital in this context, leveraging automation technology, information systems, computational simulation, and artificial intelligence to enhance production efficiency and flexibility, minimize human errors, elucidate material mechanisms, and improve product performance. Battery data analysis platforms are critical for smart manufacturing, helping researchers predict and optimize various battery properties through advanced data analysis techniques. However, current battery big data analysis platforms encounter several challenges, including issues with data integration, limited analysis tools, poor user-friendliness, and insufficient scalability. To address these challenges, we have developed efficient algorithms using machine learning techniques for common tasks in battery data analysis, including feature analysis, battery consistency evaluation, state of health estimation, and remaining useful life prediction. Furthermore, we have created a specialized big data analysis platform for batteries named BatAi Craft. This platform uses comprehensive data analysis and performance prediction to help researchers intuitively understand complex battery datasets and uncover underlying patterns and relationships. By deploying these advanced algorithms, BatAi Craft improves the efficiency of battery analysis and intelligent management, driving the digital and smart advancement of the battery industry.

Key words: lithium battery, big data, artificial intelligence, software platform, features, lifespan, SOH

中图分类号:

TP 18

焦君宇, 张全權, 陈宁波, 王冀钰, 芦秋迪, 丁浩浩, 彭鹏, 宋孝河, 张帆, 郑家新. 电池大数据智能分析平台的研发与应用[J]. 储能科学与技术, 2024, 13(9): 3198-3213.

Junyu JIAO, Quanquan ZHANG, Ningbo CHEN, Jiyu WANG, Qiudi LU, Haohao DING, Peng PENG, Xiaohe SONG, Fan ZHANG, Jiaxin ZHENG. Development and applications of an intelligent big data analysis platform for batteries[J]. Energy Storage Science and Technology, 2024, 13(9): 3198-3213.

图/表 18

图1

图2

表1

拟合公式"

拟合名称	拟合公式
线性拟合	$y = a x + b$
多项式拟合	$y = p 0 x n + p 1 x n - 1 + ⋯ + p n$
单指数拟合	$y = a e b x + c$
双指数拟合	$y = a e b x + c e d x$
指数+线性	$y = a e b x + c x + d$

表1

图3

图4

图5

图6

图7

表2

表3

图8

图9

图10

图11

表4

SOH估计结果评估"

充电模式	均方根误差(RMSE)	平均绝对误差(MAE)	平均百分比误差(MAPE)/%	判定系数( $R 2$ )
一段恒流充电	0.02	0.02	2.43	0.97
多段恒流充电	0.01	0.01	0.55	0.97

表4

图12

图13

表5

参考文献 42

1	XU X D, HAN X B, LU L G, et al. Challenges and opportunities toward long-life lithium-ion batteries[J]. Journal of Power Sources, 2024, 603: 234445. DOI: 10.1016/j.jpowsour. 2024. 234445.
2	FRITH J T, LACEY M J, ULISSI U. A non-academic perspective on the future of lithium-based batteries[J]. Nature Communications, 2023, 14(1): 420. DOI: 10.1038/s41467-023-35933-2.
3	SULZER V, MOHTAT P, AITIO A, et al. The challenge and opportunity of battery lifetime prediction from field data[J]. Joule, 2021, 5(8): 1934-1955. DOI: 10.1016/j.joule.2021.06.005.
4	FINEGAN D P, ZHU J E, FENG X N, et al. The application of data-driven methods and physics-based learning for improving battery safety[J]. Joule, 2021, 5(2): 316-329. DOI: 10.1016/j.joule.2020.11.018.
5	JIAO J Y, LAI G M, QIN S H, et al. Tuning of surface morphology in Li layered oxide cathode materials[J]. Acta Materialia, 2022, 238: 118229. DOI: 10.1016/j.actamat.2022.118229.
6	JIAO J Y, LAI G M, ZHAO L, et al. Self-healing mechanism of lithium in lithium metal[J]. Advanced Science, 2022, 9(12): e2105574. DOI: 10.1002/advs.202105574.
7	SEVERSON K A, ATTIA P M, JIN N, et al. Data-driven prediction of battery cycle life before capacity degradation[J]. Nature Energy, 2019, 4: 383-391. DOI: 10.1038/s41560-019-0356-8.
8	LU Y F, LI K, HAN X B, et al. A method of cell-to-cell variation evaluation for battery packs in electric vehicles with charging cloud data[J]. eTransportation, 2020, 6: 100077. DOI: 10.1016/j.etran.2020.100077.
9	LU J H, XIONG R, TIAN J P, et al. Deep learning to estimate lithium-ion battery state of health without additional degradation experiments[J]. Nature Communications, 2023, 14(1): 2760. DOI: 10.1038/s41467-023-38458-w.
10	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.
11	ZHAO J Y, LING H P, WANG J B, et al. Data-driven prediction of battery failure for electric vehicles[J]. iScience, 2022, 25(4): 104172. DOI: 10.1016/j.isci.2022.104172.
12	ZHAO J Y, FENG X N, TRAN M K, et al. Battery safety: Fault diagnosis from laboratory to real world[J]. Journal of Power Sources, 2024, 598: 234111. DOI: 10.1016/j.jpowsour. 2024. 234111.
13	LI Y, LIU K L, FOLEY A M, et al. Data-driven health estimation and lifetime prediction of lithium-ion batteries: A review[J]. Renewable and Sustainable Energy Reviews, 2019, 113: 109254. DOI: 10.1016/j.rser.2019.109254.
14	Battery quality analytics for cell manufacturers \| Voltaiq[EB/OL]. [2024-07-19]. https://www.voltaiq.com/
15	TWAICE battery analytics software[EB/OL]. [2024-07-19]. https://www.twaice.com/
16	BatteryArchive.org[EB/OL]. [2024-07-19]. https://batteryarchive.org/
17	SAHA B, GOEBEL K. NASA Ames Prognostics Data Repository. NASA Ames Research Center. Battery Data Set[EB/OL]. (2007).[2024-06-01]. https://phm-datasets.s3.amazonaws.com/NASA/5.+Battery+Data+Set.zip
18	YE M, WEI M, WANG Q, et al. State of health estimation for lithium-ion batteries based on incremental capacity analysis under slight overcharge voltage[J]. Frontiers in Energy Research, 2022, 10: 1001505. DOI: 10.3389/fenrg.2022.1001505.
19	SUN H L, YANG D F, DU J X, et al. Prediction of Li-ion battery state of health based on data-driven algorithm[J]. Energy Reports, 2022, 8: 442-449. DOI: 10.1016/j.egyr.2022.11.134.
20	XIONG W, XU G, LI Y M, et al. Early prediction of lithium-ion battery cycle life based on voltage-capacity discharge curves[J]. Journal of Energy Storage, 2023, 62: 106790. DOI: 10.1016/j.est.2023.106790.
21	AITIO A, HOWEY D A. Predicting battery end of life from solar off-grid system field data using machine learning[J]. Joule, 2021, 5(12): 3204-3220. DOI: 10.1016/j.joule.2021.11.006.
22	YU C, ZHU J G, WEI X Z, et al. Research on temperature inconsistency of large-format lithium-ion batteries based on the electrothermal model[J]. World Electric Vehicle Journal, 2023, 14(10): 271. DOI: 10.3390/wevj14100271.
23	TIAN Y, SHE Y, WU J F, et al. Thermal runaway propagation characteristics of lithium-ion batteries with a non-uniform state of charge distribution[J]. Journal of Solid State Electrochemistry, 2023, 27(8): 2185-2197. DOI: 10.1007/s10008-023-05496-9.
24	FENG F, HU X S, HU L, et al. Propagation mechanisms and diagnosis of parameter inconsistency within Li-Ion battery packs[J]. Renewable and Sustainable Energy Reviews, 2019, 112: 102-113. DOI: 10.1016/j.rser.2019.05.042.
25	OUYANG M G, ZHANG M X, FENG X N, et al. Internal short circuit detection for battery pack using equivalent parameter and consistency method[J]. Journal of Power Sources, 2015, 294: 272-283. DOI: 10.1016/j.jpowsour.2015.06.087.
26	XIA B, SHANG Y L, NGUYEN T, et al. A correlation based fault detection method for short circuits in battery packs[J]. Journal of Power Sources, 2017, 337: 1-10. DOI: 10.1016/j.jpowsour. 2016.11.007.
27	XUE Q, LI G, ZHANG Y J, et al. Fault diagnosis and abnormality detection of lithium-ion battery packs based on statistical distribution[J]. Journal of Power Sources, 2021, 482: 228964. DOI: 10.1016/j.jpowsour.2020.228964.
28	WANG Z L, ZHAO X Y, FU L, et al. A review on rapid state of health estimation of lithium-ion batteries in electric vehicles[J]. Sustainable Energy Technologies and Assessments, 2023, 60: 103457. DOI: 10.1016/j.seta.2023.103457.
29	SALDAÑA G, MARTÍN J I S, ZAMORA I, et al. Empirical electrical and degradation model for electric vehicle batteries[J]. IEEE Access, 2020, 8: 155576-155589. DOI: 10.1109/ACCESS. 2020.3019477.
30	LIU S L, DONG X, YU X D, et al. A method for state of charge and state of health estimation of lithium-ion battery based on adaptive unscented Kalman filter[J]. Energy Reports, 2022, 8: 426-436. DOI: 10.1016/j.egyr.2022.09.093.
31	LI J, ADEWUYI K, LOTFI N, et al. A single particle model with chemical/mechanical degradation physics for lithium ion battery State of Health (SOH) estimation[J]. Applied Energy, 2018, 212: 1178-1190. DOI: 10.1016/j.apenergy.2018.01.011.
32	CHEN Z, SUN M M, SHU X, et al. Online state of health estimation for lithium-ion batteries based on support vector machine[J]. Applied Sciences, 2018, 8(6): 925. DOI: 10.3390/app8060925.
33	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.
34	BAGHDADI I, BRIAT O, GYAN P, et al. State of health assessment for lithium batteries based on voltage-time relaxation measure[J]. Electrochimica Acta, 2016, 194: 461-472. DOI: 10.1016/j.electacta.2016.02.109.
35	YAO J W, POWELL K, GAO T. A two-stage deep learning framework for early-stage lifetime prediction for lithium-ion batteries with consideration of features from multiple cycles[J]. Frontiers in Energy Research, 2022, 10: 1059126. DOI: 10.3389/fenrg.2022.1059126.
36	ZHAO J, ZHU Y, ZHANG B, et al. Review of state estimation and remaining useful life prediction methods for lithium-ion batteries[J]. Sustainability, 2023, 15(6): 5014.
37	WU T Z, ZHAO T, XU S Y. Prediction of remaining useful life of the lithium-ion battery based on improved particle filtering[J]. Frontiers in Energy Research, 2022, 10: 863285. DOI: 10.3389/fenrg.2022.863285.
38	WANG X X, YE P L, LIU S R, et al. Research progress of battery life prediction methods based on physical model[J]. Energies, 2023, 16(9): 3858. DOI: 10.3390/en16093858.
39	PARK K, CHOI Y, CHOI W J, et al. LSTM-based battery remaining useful life prediction with multi-channel charging profiles[J]. IEEE Access, 2020, 8: 20786-20798. DOI: 10.1109/ACCESS.2020.2968939.
40	ZHANG H, ALTAF F, WIK T. Battery capacity knee-onset identification and early prediction using degradation curvature[J]. Journal of Power Sources, 2024, 608: 234619. DOI: 10.1016/j.jpowsour.2024.234619.
41	IBRAHEEM R, WU Y, LYONS T, et al. Early prediction of lithium-ion cell degradation trajectories using signatures of voltage curves up to 4-minute sub-sampling rates[J]. Applied Energy, 2023, 352: 121974. DOI: 10.1016/j.apenergy.2023.121974.
42	BACHMANN R, MIZRAHI D, ATANOV A, et al. MultiMAE: multi-modal multi-task masked autoencoders[M]//Lecture Notes in Computer Science. Cham: Springer Nature Switzerland, 2022: 348-367. DOI: 10.1007/978-3-031-19836-6_20.

特征	名称	皮尔逊相关性系数
Q_sum	片段累计充电量	0.98
V_IDR	片段电压十分位距	0.93
vq_s21	片段容量电压曲线下面积	0.87
E_entropy	片段能量曲线熵	0.82
V_var	片段电压方差	0.76
E_slope_total	片段始末能量变化斜率	0.75
T_slope_equal_time	片段内等时间温度变化斜率	0.64
Q_incremental_equal_time	片段内等时间电量增量	0.58
Q_entropy	片段电量曲线熵	0.48
T_IQR	片段温度四分位距	0.41

特征	名称	皮尔逊相关性系数
Log_Var_Q	等压点容量差方差	0.93
Log_IQR_dQdV	等压点增量容量差四分位距	0.76
Log_IQR_Q	等压点容量差四分位距	0.76
Final_peak_loc_dQdV	结束增量容量曲线峰位置	0.72
Max_lower_area_voltage	电压曲线下面积最大值	0.68
Log_Min_dQdV	等压点增量容量差最小值	0.67
Log_Var_time	等压点放电时间差方差	0.54
intercept_root	均方根衰减模型截距	0.53
intercept_linear	线性衰减模型截距	0.52
Upper_area_voltage	电压曲线上面积差值	0.46
Discharge_cc_time_final	结束循环恒流放电时间	0.34
Initial_SoH	初始SOH	0.33

任务	均方根误差(RMSE)循环	平均绝对误差(MAE)循环	平均百分比误差(MAPE)/%
循环寿命	74.42	48.33	5.39
衰减轨迹膝点法	46.52	37.46	6.14
衰减轨迹SOH法	51.52	39.14	6.96

[1]	陈星光, 沈逸凡, 邵裕新, 郑岳久, 孙涛, 来鑫, 沈凯, 韩雪冰. 面向实车应用的磷酸铁锂电池容量辨识及特异性优化方法研究[J]. 储能科学与技术, 2024, 13(9): 2963-2971.
[2]	袁誉杭, 高宇辰, 张俊东, 高岩斌, 王超珑, 陈翔, 张强. 大语言模型在储能研究中的应用[J]. 储能科学与技术, 2024, 13(9): 2907-2919.
[3]	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.
[4]	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.
[5]	黄家辉, 邝祝芳. 人工智能与储能技术融合的前沿发展[J]. 储能科学与技术, 2024, 13(9): 3161-3181.
[6]	黎耀康, 杨海东, 徐康康, 蓝昭宇, 章润楠. 基于加权UMAP和改进BLS的锂电池温度预测[J]. 储能科学与技术, 2024, 13(9): 3006-3015.
[7]	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.
[8]	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.
[9]	刘莹, 孙丙香, 赵鑫泽, 张珺玮. 基于电热耦合模型的宽温域锂离子电池SOC/SOP联合估计[J]. 储能科学与技术, 2024, 13(9): 3030-3041.
[10]	许晶, 王宇琦, 符晓, 杨其凡, 连景臣, 王力奇, 肖睿娟. 基于大数据的电池新材料设计[J]. 储能科学与技术, 2024, 13(9): 2920-2932.
[11]	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.
[12]	朱振威, 苗嘉伟, 祝夏雨, 王晓旭, 邱景义, 张浩. 基于机器学习方法的锂电池剩余寿命预测研究进展[J]. 储能科学与技术, 2024, 13(9): 3134-3149.
[13]	张新新, 岑官骏, 乔荣涵, 朱璟, 郝峻丰, 孙蔷馥, 田孟羽, 金周, 詹元杰, 闫勇, 贲留斌, 俞海龙, 刘燕燕, 周洪, 黄学杰. 锂电池百篇论文点评（2024.06.01—2024.07.31）[J]. 储能科学与技术, 2024, 13(9): 3226-3244.
[14]	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.
[15]	杨凯悦, 谢欣兵, 杜晓钟. 基于离散元法的锂电池极片辊压过程探究[J]. 储能科学与技术, 2024, 13(8): 2570-2579.

电池大数据智能分析平台的研发与应用

Development and applications of an intelligent big data analysis platform for batteries

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 18

参考文献 42

相关文章 15

编辑推荐

Metrics

本文评价