基于电化学阻抗特征选择和高斯过程回归的锂离子电池健康状态估计方法

doi:10.19799/j.cnki.2095-4239.2022.0150

储能科学与技术 ›› 2022, Vol. 11 ›› Issue (9): 2995-3002.doi: 10.19799/j.cnki.2095-4239.2022.0150

基于电化学阻抗特征选择和高斯过程回归的锂离子电池健康状态估计方法

陈晓宇¹(), 耿萌萌², 王乾坤¹, 沈佳妮¹, 贺益君¹(), 马紫峰¹

^1.上海交通大学化学工程系，上海 200240
^2.中国电力科学研究院有限公司，北京 100192

收稿日期:2022-03-23 修回日期:2022-04-26 出版日期:2022-09-05 发布日期:2022-08-30
通讯作者: 贺益君 E-mail:chenxiaoyu1997@sjtu.edu.cn;heyijun@sjtu.edu.cn
作者简介:陈晓宇（1998—），男，硕士研究生，从事电池健康状态研究，E-mail：chenxiaoyu1997@sjtu.edu.cn；
基金资助:
国家电网公司总部科技项目“基于交流阻抗的储能电池状态在线感知技术研究”(5419-202055246A-0-0-00)

Electrochemical impedance feature selection and gaussian process regression based on the state-of-health estimation method for lithium-ion batteries

Xiaoyu CHEN¹(), Mengmeng GENG², Qiankun WANG¹, Jiani SHEN¹, Yijun HE¹(), Zifeng MA¹

^1.Department of Chemical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
^2.China Electric Power Research Institute, Beijing 100192, China

Received:2022-03-23 Revised:2022-04-26 Online:2022-09-05 Published:2022-08-30
Contact: Yijun HE E-mail:chenxiaoyu1997@sjtu.edu.cn;heyijun@sjtu.edu.cn

摘要/Abstract

摘要：

电化学阻抗谱(electrochemical impedance spectroscopy，EIS)蕴含丰富的电池健康状态(state of health，SOH)信息，但不同频率的电化学阻抗数据间并不相互独立，直接利用全频段EIS数据构建SOH估计模型，往往存在精度低、计算复杂度高等问题。鉴于此，本文提出了一种基于特征选择和高斯过程回归的SOH估计方法，可通过序贯前向搜索策略，结合交叉验证均方根误差指标，逐步搜索阻抗特征子集。基于此，采用基于水平图的多目标可视化决策方法，以均衡模型复杂度与精度为目标，综合考虑特征个数与交叉验证均方根误差，实施阻抗特征子集优选。所提方法已成功地应用于公开发表数据集。相比全频段EIS建模方法，本文作者所提方法可显著提升SOH估计精度，大幅降低EIS测试时间，为电化学阻抗技术应用于SOH在线估计提供理论和技术支撑。

关键词: 锂离子电池, 健康状态, 电化学阻抗谱, 特征选择, 高斯过程回归

Abstract:

Electrochemical impedance spectroscopy (EIS) contains rich information about the battery state of health (SOH). However, due to the correlation of EIS data at different frequencies, the SOH estimation model constructed from the whole frequency range of EIS data may have poor performance and high complexity. Therefore, this study proposes an SOH estimation method with feature selection and Gaussian process regression by combining sequential forward search and cross-validation to seek the feature set. A level diagram method was adopted to formulate model performance evaluation indicators based on the number of features and the estimation error, which aimed to balance model complexity and model estimation accuracy. A public dataset was used to validate the proposed method, and the results showed that the proposed model with feature selection could achieve higher accuracy and less time for the EIS test than the model constructed from the whole frequency range of EIS data. This study provides theoretical and technical support for applying EIS to online SOH estimation.

Key words: lithium-ion battery, state of health, electrochemical impedance spectroscopy, feature selection, gaussian process regression

中图分类号:

TM 912

陈晓宇, 耿萌萌, 王乾坤, 沈佳妮, 贺益君, 马紫峰. 基于电化学阻抗特征选择和高斯过程回归的锂离子电池健康状态估计方法[J]. 储能科学与技术, 2022, 11(9): 2995-3002.

Xiaoyu CHEN, Mengmeng GENG, Qiankun WANG, Jiani SHEN, Yijun HE, Zifeng MA. Electrochemical impedance feature selection and gaussian process regression based on the state-of-health estimation method for lithium-ion batteries[J]. Energy Storage Science and Technology, 2022, 11(9): 2995-3002.

图/表 9

图1

图2

图3

图4

图5

图6

图7

表1

表2

参考文献 23

1	LU L G, HAN X B, LI J Q, et al. A review on the key issues for lithium-ion battery management in electric vehicles[J]. Journal of Power Sources, 2013, 226: 272-288.
2	HAN X B, LU L G, ZHENG Y J, et al. A review on the key issues of the lithium ion battery degradation among the whole life cycle[J]. eTransportation, 2019, 1: 100005.
3	CHENG K W E, DIVAKAR B P, WU H J, et al. Battery-management system (BMS) and SOC development for electrical vehicles[J]. IEEE Transactions on Vehicular Technology, 2011, 60(1): 76-88.
4	NG M F, ZHAO J, YAN Q Y, et al. Predicting the state of charge and health of batteries using data-driven machine learning[J]. Nature Machine Intelligence, 2020, 2(3): 161-170.
5	ZHENG L F, ZHANG L, ZHU J G, et al. Co-estimation of state-of-charge, capacity and resistance for lithium-ion batteries based on a high-fidelity electrochemical model[J]. Applied Energy, 2016, 180: 424-434.
6	LAI X, ZHENG Y J, SUN T. A comparative study of different equivalent circuit models for estimating state-of-charge of lithium-ion batteries[J]. Electrochimica Acta, 2018, 259: 566-577.
7	KIM J, CHO B H. State-of-charge estimation and state-of-health prediction of a Li-ion degraded battery based on an EKF combined with a per-unit system[J]. IEEE Transactions on Vehicular Technology, 2011, 60(9): 4249-4260.
8	BI J, ZHANG T, YU H Y, et al. State-of-health estimation of lithium-ion battery packs in electric vehicles based on genetic resampling particle filter[J]. Applied Energy, 2016, 182: 558-568.
9	SALKIND A J, FENNIE C, SINGH P, et al. Determination of state-of-charge and state-of-health of batteries by fuzzy logic methodology[J]. Journal of Power Sources, 1999, 80(1/2): 293-300.
10	ANDRE D, NUHIC A, SOCZKA-GUTH T, et al. Comparative study of a structured neural network and an extended Kalman filter for state of health determination of lithium-ion batteries in hybrid electricvehicles[J]. Engineering Applications of Artificial Intelligence, 2013, 26(3): 951-961.
11	HE Y J, SHEN J N, SHEN J F, et al. State of health estimation of lithium-ion batteries: A multiscale Gaussian process regression modeling approach[J]. AIChE Journal, 2015, 61(5): 1589-1600.
12	庄全超, 徐守冬, 邱祥云, 等. 锂离子电池的电化学阻抗谱分析[J]. 化学进展, 2010, 22(6): 1044-1057.
	ZHUANG Q C, XU S D, QIU X Y, et al. Diagnosis of electrochemical impedance spectroscopy in lithium ion batteries[J]. Progress in Chemistry, 2010, 22(6): 1044-1057.
13	HUET F. A review of impedance measurements for determination of the state-of-charge or state-of-health of secondary batteries[J]. Journal of Power Sources, 1998, 70(1): 59-69.
14	刘海洋. 基于阻抗谱时域测量的锂离子电池健康状态估计研究[D]. 哈尔滨: 哈尔滨工业大学, 2018.
	LIU H Y. Research on state of health estimation of lithium ion batteries based on time domian electrochemical impedance spectroscopy measurement[D]. Harbin: Harbin Institute of Technology, 2018.
15	STROE D I, SWIERCZYNSKI M, STAN A I, et al. Diagnosis of lithium-ion batteries state-of-health based on electrochemical impedance spectroscopy technique[C]//2014 IEEE Energy Conversion Congress and Exposition. September 14-18, 2014, Pittsburgh, PA, USA. IEEE, 2014: 4576-4582.
16	GALEOTTI M, CINÀ L, GIAMMANCO C, et al. Performance analysis and SOH (state of health) evaluation of lithium polymer batteries through electrochemical impedance spectroscopy[J]. Energy, 2015, 89: 678-686.
17	ZHU S, SUN X Y, GAO X Y, et al. Equivalent circuit model recognition of electrochemical impedance spectroscopy via machine learning[J]. Journal of Electroanalytical Chemistry, 2019, 855: 113627.
18	ZHANG Y W, TANG Q C, ZHANG Y, et al. Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning[J]. Nature Communications, 2020, 11: 1706.
19	UNGUREAN L, CÂRSTOIU G, MICEA M V, et al. Battery state of health estimation: A structured review of models, methods and commercial devices[J]. International Journal of Energy Research, 2017, 41(2): 151-181.
20	SUN Z H, BEBIS G, MILLER R. Object detection using feature subset selection[J]. Pattern Recognition, 2004, 37(11): 2165-2176.
21	何志昆, 刘光斌, 赵曦晶, 等. 高斯过程回归方法综述[J]. 控制与决策, 2013, 28(8): 1121-1129, 1137.
	HE Z K, LIU G B, ZHAO X J, et al. Overview of Gaussian process regression[J]. Control and Decision, 2013, 28(8): 1121-1129, 1137.
22	BLASCO X, HERRERO J M, SANCHIS J, et al. A new graphical visualization of n-dimensional Pareto front for decision-making in multiobjective optimization[J]. Information Sciences, 2008, 178(20): 3908-3924.
23	MOMMA T, MATSUNAGA M, MUKOYAMA D, et al. Ac impedance analysis of lithium ion battery under temperature control[J]. Journal of Power Sources, 2012, 216: 304-307.

特征选择策略	优选特征子集包含特征个数	训练集交叉验证RMSE	测试集SOH 估计RMSE
SFS-1	1	0.23%	5.9%
SFS-4	4	0.18%	6.0%
SFS-LD	18	0.03%	4.2%
SFS-MIN	61	0.02%	5.4%

[1]	邓林旺, 冯天宇, 舒时伟, 张子峰, 郭彬. 锂离子电池快充策略技术研究进展[J]. 储能科学与技术, 2022, 11(9): 2879-2890.
[2]	栗志展, 秦金磊, 梁嘉宁, 李峥嵘, 王瑞, 王得丽. 高镍三元层状锂离子电池正极材料：研究进展、挑战及改善策略[J]. 储能科学与技术, 2022, 11(9): 2900-2920.
[3]	牛少军, 吴凯, 朱国斌, 王艳, 曲群婷, 郑洪河. 锂离子电池硅基负极循环过程中的膨胀应力[J]. 储能科学与技术, 2022, 11(9): 2989-2994.
[4]	张群斌, 董陶, 李晶晶, 刘艳侠, 张海涛. 废旧电池电解液回收及高值化利用研发进展[J]. 储能科学与技术, 2022, 11(9): 2798-2810.
[5]	贡淑雅, 王跃, 李萌, 邱景义, 王洪, 文越华, 徐斌. 锂离子电池负极材料TiNb₂O₇ 的研究进展[J]. 储能科学与技术, 2022, 11(9): 2921-2932.
[6]	卓萍, 朱艳丽, 齐创, 王聪杰, 高飞. 锂离子电池组过充燃烧爆炸特性[J]. 储能科学与技术, 2022, 11(8): 2471-2479.
[7]	曹志成, 周开运, 朱家立, 刘高明, 严慜, 汤舜, 曹元成, 程时杰, 张炜鑫. 锂离子电池储能系统消防技术的中国专利分析[J]. 储能科学与技术, 2022, 11(8): 2664-2670.
[8]	霍丽萍, 栾伟玲, 庄子贤. 锂离子电池储能安全技术的发展态势[J]. 储能科学与技术, 2022, 11(8): 2671-2680.
[9]	张越, 孔得朋, 平平. 液冷板抑制锂离子电池组热失控蔓延性能及优化设计[J]. 储能科学与技术, 2022, 11(8): 2432-2441.
[10]	徐成善, 鲁博瑞, 张梦启, 王淮斌, 金昌勇, 欧阳明高, 冯旭宁. 储能锂离子电池预制舱热失控烟气流动研究[J]. 储能科学与技术, 2022, 11(8): 2418-2431.
[11]	韦荣阳, 毛阗, 高晗, 彭建仁, 杨健. 基于TWP-SVR的锂离子电池健康状态估计[J]. 储能科学与技术, 2022, 11(8): 2585-2599.
[12]	马勇, 李晓涵, 孙磊, 郭东亮, 杨景刚, 刘建军, 肖鹏, 钱广俊. 基于三维电化学热耦合析锂模型的锂离子电池参数设计[J]. 储能科学与技术, 2022, 11(8): 2600-2611.
[13]	唐亮, 尹小波, 吴候福, 刘鹏杰, 王青松. 电化学储能产业发展对安全标准的需求[J]. 储能科学与技术, 2022, 11(8): 2645-2652.
[14]	喻航, 张英, 徐超航, 余思瀚. 锂电储能系统热失控防控技术研究进展[J]. 储能科学与技术, 2022, 11(8): 2653-2663.
[15]	赵亚文, 黄彧, 张言茹. 轨道交通动力锂离子电池安全性测试标准分析[J]. 储能科学与技术, 2022, 11(8): 2505-2518.

基于电化学阻抗特征选择和高斯过程回归的锂离子电池健康状态估计方法

Electrochemical impedance feature selection and gaussian process regression based on the state-of-health estimation method for lithium-ion batteries

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 23

相关文章 15

编辑推荐

Metrics

本文评价