数据驱动的锂离子电池健康状态综合评分及异常电池筛选

doi:10.3901/JME.2021.14.141

机械工程学报 ›› 2021, Vol. 57 ›› Issue (14): 141-149,159.doi: 10.3901/JME.2021.14.141

• 特邀专栏：电源系统设计、管理与大数据 • 上一篇下一篇

扫码分享

数据驱动的锂离子电池健康状态综合评分及异常电池筛选

贾俊¹, 胡晓松¹, 邓忠伟¹, 徐华池², 肖伟², 韩锋³

1. 重庆大学汽车工程学院重庆 400044;
2. 清华四川能源互联网研究院成都 610213;
3. 重庆长安新能源汽车科技有限公司重庆 401133

收稿日期:2020-06-14 修回日期:2021-02-20 出版日期:2021-09-15 发布日期:2021-09-15
通讯作者: 邓忠伟(通信作者),男,1990年出生,博士,博士后,助理研究员。主要研究方向为动力电池及储能系统管理控制技术。E-mail:dengzhongw@cqu.edu.cn
作者简介:贾俊,男,1995年出生。主要研究方向为数据驱动的锂电池健康管理算法及应用。E-mail:junjia@cqu.edu.cn
基金资助:
国家自然科学基金（51875054）、重庆市杰出青年科学基金（cstc2019jcyjjq0010）和重庆市技术创新与应用发展专项重点（cstc2019jscx-mbdxX0029）资助项目

Data-driven Comprehensive Evaluation of Lithium-ion Battery State of Health and Abnormal Battery Screening

JIA Jun¹, HU Xiaosong¹, DENG Zhongwei¹, XU Huachi², XIAO Wei², HAN Feng³

1. Department of Automotive Engineering, Chongqing University, Chongqing 400044;
2. Tsinghua Sichuan Energy Internet Research Institute, Chengdu 610213;
3. Changan New Energy Automobile Technology Co., Ltd., Chongqing 401133

Received:2020-06-14 Revised:2021-02-20 Online:2021-09-15 Published:2021-09-15

摘要/Abstract

摘要： 锂离子电池是电动汽车和储能系统最重要的组成部分，其故障预测和健康管理对于运行维护至关重要。数据驱动的方法较基于模型的方法更适合大规模工程应用，针对实际应用中工况复杂和数据质量较差的场景，提出数据驱动的健康状态综合评分及异常筛选算法，具有较强的适应性。首先，针对电池实际运行工况提出一种新的特征提取方案，可适用于非恒流的不稳定工况。开发了基于多维特征和混合聚类算法的健康状态综合评分体系，该方案采用无监督学习的算法框架，对可提取特征的数量和质量要求不高，无需进行事先的模型训练和复杂的超参数调整。然后，在麻省理工学院和斯坦福大学提供的公开数据集进行了算法验证，基于电池生命周期各阶段特征集进行健康度等级预测，并应用于健康度高低分选，均能达到92%以上的准确率。在某用户侧储能电站实现了该算法的应用，采用早期运行数据即可快速筛选异常电池，有利于尽早维护，提高电池系统的安全性和经济性。

关键词: 锂离子电池, 特征提取, 健康状态, 异常电池筛选, 故障预测和健康管理

Abstract: Lithium-ion batteries are the most important part of electric vehicles and energy storage systems, and their health management and fault identification are critical to operation and maintenance. The data-driven method is more suitable for large-scale engineering applications than the model-based method. Aiming at scenarios with complex working conditions and poor data quality in practical applications, a data-driven comprehensive evaluation of lithium-ion battery state of health and abnormal battery screening algorithm are proposed. First, a novel feature extraction scheme is proposed for the actual operating conditions of batteries, which can be applied to unstable working conditions with non-constant current. A comprehensive state of health scoring system based on multi-dimensional features and hybrid clustering algorithms is developed. This scheme is an algorithm framework for unsupervised learning, which does not require high quantity and quality of extractable features, without prior model training and complicated hyper parameter adjustment. Then, the algorithm is verified at the public data set of Massachusetts Institute of Technology and Stanford. Based on the feature set of each stage of the battery life cycle, the health level prediction can be achieved, and the accuracy is more than 92% when applied to classify the health level. Finally, the proposed algorithm is implemented in a user-side energy storage power station. Early operation data can be used to quickly screen abnormal batteries, which is beneficial to early maintenance, and improve the safety and economy of the battery system.

Key words: lithium-ion battery, feature extraction, state of health, abnormal battery screening, prognostics and health management

中图分类号:

TM912

贾俊, 胡晓松, 邓忠伟, 徐华池, 肖伟, 韩锋. 数据驱动的锂离子电池健康状态综合评分及异常电池筛选[J]. 机械工程学报, 2021, 57(14): 141-149,159.

JIA Jun, HU Xiaosong, DENG Zhongwei, XU Huachi, XIAO Wei, HAN Feng. Data-driven Comprehensive Evaluation of Lithium-ion Battery State of Health and Abnormal Battery Screening[J]. Journal of Mechanical Engineering, 2021, 57(14): 141-149,159.

参考文献

[1] 戴海峰,周艳新,顾伟军,等. 电动汽车用动力锂离子电池寿命问题研究综述[J]. 电源技术,2014(10):182-184,212. DAI Haifeng,ZHOU Yanxin,GU Weijun,et al. A review of researches on the life of power lithium-ion batteries for electric vehicles[J]. Power Technology,2014(10):182-184,212.
[2] HU Xiaosong,ZHANG Kai,LIU Kailong,et al. Advanced fault diagnosis for lithium-Ion battery systems[J/OL]. TechRxiv. Preprint.[2020-03-02]. https://doi.org/10.36227/techrxiv.11777448.v1
[3] 胡晓松,唐小林. 电动车辆锂离子动力电池建模方法综述[J]. 机械工程学报,2017,53(16):34-45. HU Xiaosong,TANG Xiaolin. Review of modeling techniques for lithium-ion traction batteries in electric vehicles[J]. Journal of Mechanical Engineering,2017,53(16):20-31.
[4] QIANG Jiaxi,AO Guoqiang,YANG Lin. Estimation method on the battery state of charge for hybrid electric vehicle[J]. Chinese Journal of Mechanical Engineering,2008,21(3):20-25.
[5] LIU Zhentong,HE Hongwen. Model-based sensor fault diagnosis of a lithium-ion battery in electric vehicles[J]. Energies,2015,8(7):6509-6527.
[6] Odendaal H M,Jones T. Actuator fault detection and isolation:An optimised parity space approach[J]. Control Engineering Practice,2014,26:222-232.
[7] 任东生,冯旭宁,韩雪冰,等. 锂离子电池全生命周期安全性演变研究进展[J]. 储能科学与技术,2018,7(6):9-18. REN Dongsheng,FENG Xuning,HAN Xuebing,et al. Research progress on the life cycle safety evolution of lithium-ion batteries[J]. Energy Storage Science and Technology,2018,7(6):9-18.
[8] 徐兴,徐琪凌,王峰,等. 车用锂离子动力电池电化学模型修正方法[J]. 机械工程学报,2019,55(12):128-136. XU Xing,XU Qiling,WANG Feng,et al. Modification method of electrochemical model of lithium ion power battery for vehicles[J]. Journal of Mechanical Engineering,2019,55(12):128-136.
[9] 戴海峰,孙泽昌,魏学哲. 利用双卡尔曼滤波算法估计电动汽车用锂离子动力电池的内部状态[J]. 机械工程学报,2009,45(6):95-101. DAI Haifeng,SUN Zechang,WEI Xuezhe. Using dual Kalman filtering algorithm to estimate the internal state of lithium ion power battery for electric vehicles[J]. Journal of Mechanical Engineering,2009,45(6):95-101.
[10] 彭宇,刘大同. 数据驱动故障预测和健康管理综述[J]. 仪器仪表学报,2014(3):3-17. PENG Yu,LIU Datong. Overview of data-driven fault prediction and health management[J]. Journal of Chinese Instrumentation,2014(3):3-17.
[11] Xiao W,Xu h c,Jia J,et al. State of health estimation framework of li-on battery based on improved Gaussian process regression for real car data[J]. IOP Conference Series:Materials Science and Engineering,2020(793):012063.
[12] Zhao Y,Liu P,Wang Z,et al. Fault and defect diagnosis of battery for electric vehicles based on big data analysis methods[J]. Applied Energy,2017(207):354-362.
[13] Hong J,Wang Z,Liu P. Big-data-based thermal runaway prognosis of battery systems for electric vehicles[J]. Energies,2017,10:919.
[14] 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(5):1-9.
[15] Hu Xiaosong,Xu Le,Lin Xianke,et al. Battery lifetime prognostics[J]. Joule,2020(4):1-37.
[16] 廖芹,郝志峰,陈志宏. 数据挖掘与数学建模[M]. 北京:国防工业出版社,2010. LIAO Qin,HAO Zhifeng,CHEN Zhihong. Data mining and mathematical modeling[M]. Beijing:National Defense Industry Press,2010.
[17] Feng F,Hu X,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.
[18] Zheng Y,Han X,Lu L,et al. Lithium ion battery pack power fade fault identification based on Shannon entropy in electric vehicles[J]. Journal of Power Sources,2013(223):136-146.
[19] Hu X,Jiang J,Cao D,et al. Battery health prognosis for electric vehicles using sample entropy and sparse bayesian predictive modeling[J]. IEEE Transactions on Industrial Electronics,2015,63(4):2645-2656.
[20] Weng C,Cui Y,Sun J,et al. On-board state of health monitoring of lithium-ion batteries using incremental capacity analysis with support vector regression[J]. Journal of Power Sources,2013,235:36-44.
[21] Malhi A,Gao R X. PCA-based feature selection scheme for machine defect classification[J]. IEEE Transactions on Instrumentation & Measurement,2004,53(6):1517-1525.
[22] 孙吉贵,刘杰,赵连宇. 聚类算法研究[J]. 软件学报,2008,19(1):48-61. SUN Jigui,LIU Jie,ZHAO Lianyu. Research on clustering algorithms[J]. Journal of Software,2008,19(1):48-61.

数据驱动的锂离子电池健康状态综合评分及异常电池筛选

Data-driven Comprehensive Evaluation of Lithium-ion Battery State of Health and Abnormal Battery Screening

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	苗宝权, 陈长征, 罗园庆, 赵思雨. 基于自适应增强差分积形态滤波器的滚动轴承故障特征提取方法[J]. 机械工程学报, 2021, 57(9): 78-88.
[2]	巫晓康, 赵欢, 唐敏杰, 丁汉. 面向动作识别的旋转投影变换关节特征骨架描述[J]. 机械工程学报, 2021, 57(5): 19-30.
[3]	熊瑞, 马骕骁, 陈泽宇, 孙逢春. 锂离子电池极速自加热中的电-热耦合特性及建模[J]. 机械工程学报, 2021, 57(2): 179-189.
[4]	唐敏杰, 赵欢, 丁汉. 二进制点云局部特征描述子研究[J]. 机械工程学报, 2021, 57(2): 219-229.
[5]	周子游, 刘永刚, 杨阳, 陈峥, 舒星, 秦大同. 考虑混杂充电数据的锂离子电池容量估计[J]. 机械工程学报, 2021, 57(14): 1-9.
[6]	匡柯, 孙跃东, 任东生, 韩雪冰, 郑岳久, 耿兆杰. 车用锂离子电池电化学-热耦合高效建模方法[J]. 机械工程学报, 2021, 57(14): 10-22.
[7]	江发潮, 章方树, 徐成善, 李成, 王书洋, 任毅, 冯旭宁. 车用锂离子电池系统热蔓延试验与机理研究[J]. 机械工程学报, 2021, 57(14): 23-31.
[8]	蔡雪, 张彩萍, 张琳静, 张维戈, 高乐. 基于等效电路模型的锂离子电池峰值功率估计的对比研究[J]. 机械工程学报, 2021, 57(14): 64-76.
[9]	王学远, 李日康, 魏学哲, 戴海峰, 郑岳久. 基于传荷电阻的锂离子电池剩余寿命预测研究[J]. 机械工程学报, 2021, 57(14): 105-117.
[10]	舒星, 刘永刚, 申江卫, 陈峥. 基于改进最小二乘支持向量机与Box-Cox变换的锂离子电池容量预测[J]. 机械工程学报, 2021, 57(14): 118-128.
[11]	赵学智, 叶邦彦, 陈统坚. 频率添加奇异值分解算法及其在故障特征提取中的应用[J]. 机械工程学报, 2021, 57(10): 10-20.
[12]	杨瑞鑫, 熊瑞, 孙逢春. 锂离子动力电池外部短路测试平台开发与试验分析 ^*[J]. 电气工程学报, 2021, 16(1): 103-118.
[13]	王志学, 刘献礼, 李茂月, LIANG S Y, 王力翚, 李玉强, 孟博洋. 切削加工颤振智能监控技术[J]. 机械工程学报, 2020, 56(24): 1-23.
[14]	向兆军, 胡凤玲, 罗明华, 方崇全, 胡晓松. 基于电池组模型和聚类算法的锂离子电池组SOC不一致估计[J]. 机械工程学报, 2020, 56(18): 154-163.
[15]	朱晓庆, 王震坡, WANG Hsin, 王聪. 锂离子动力电池热失控与安全管理研究综述[J]. 机械工程学报, 2020, 56(14): 91-118.