基于间接健康指标的高斯过程回归对锂电池SOH预测

doi:10.19799/j.cnki.2095-4239.2022.0611

摘要/Abstract

摘要：

锂电池性能会随使用时间增加而逐步退化，若更换不及时，可能造成爆炸等严重事故。快速准确预测电池健康状态(state of health，SOH)，对于锂电池系统管理和维护以及安全使用至关重要。本工作提出一种基于间接健康指标(health indicators，HIs)和高斯过程回归(Gaussian process regression，GPR)相结合预测锂电池SOH的机器学习模型。首先，通过分析锂电池放电过程，提取若干易于获得且适合动态操作的直接外部特征作为间接健康指标，并计算它们和SOH的相关性，最终筛选出平均放电电压、等压降放电时间、最高放电温度和平台期放电电压初始骤降值作为健康指标；其次，以上述健康指标作为输入特征，利用GPR算法建立锂电池退化模型，对NASA锂电池数据集进行预测，平均绝对误差(mean absolute error，MAE)不超过2%，均方根误差(root mean square error，RSME)控制在4%之内；最后，将本工作模型与其他常用机器学习模型进行比较，再将模型带入不同实验条件的电池中进行泛化性能分析，最大预测误差控制在6%之内，实验结果表明，本工作提出的间接健康指标和GPR模型具有相对较高的预测精度和优秀的泛化能力。

关键词: 健康指标, 健康状态, 高斯过程回归, 支持向量机回归

Abstract:

The performance of a lithium battery degrades gradually with increasing use time. If the replacement is not completed on time, serious accidents such as explosions may occur. Rapid and accurate prediction of battery state of health (SOH) is critical for lithium battery system management, maintenance, and safe use. In this paper, a machine learning model based on indirect His (health indicators) and GPR (Gaussian process regression) is proposed to predict the SOH of lithium batteries. First, the analysis of the lithium battery discharge process extracts some easily available and suitable for the direct external features of dynamic operations as indirect His, and their correlation with SOH, eventually selecting average discharge voltage, such as pressure drop discharge time, maximum discharge temperature, and platform stage discharge voltage initial plummet in value as the health index. Second, using the above mentioned His as input features, the GPR algorithm is used to establish a lithium battery degradation model, and the MAE (mean absolute error) is less than 2% for the prediction of NASA lithium battery datasets, while the RMSE is kept within 4%. Finally, the model is compared to other commonly used machine learning models, and then into multiple experimental conditions of battery model generalization performance analysis, control about 6% of the maximum error of the prediction. The experimental results show that the proposed indirect His and GPR have relatively higher prediction precision and good generalization ability.

Key words: health indicators, state of health, Gaussian process regression, support vector regression

中图分类号:

TM 912

王瑞洁, 惠周利, 杨明. 基于间接健康指标的高斯过程回归对锂电池SOH预测[J]. 储能科学与技术, 2023, 12(2): 560-569.

Ruijie WANG, Zhouli HUI, Ming YANG. Gaussian process regression based on indirect health indicators for SOH estimation of lithium battery[J]. Energy Storage Science and Technology, 2023, 12(2): 560-569.

图/表 10

图1

图2

图3

图4

表1

图5

图6

图7

表2

图8

参考文献 24

1	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: doi: 10.1016/j.jpowsour.2021.230774.
2	TIAN H X, QIN P L, LI K, et al. A review of the state of health for lithium-ion batteries: Research status and suggestions[J]. Journal of Cleaner Production, 2020, 261: doi: 10.1016/j.jclepro. 2020.120813.
3	RAHIMI-EICHI H, OJHA U, BARONTI F, et al. Battery management system: An overview of its application in the smart grid and electric vehicles[J]. IEEE Industrial Electronics Magazine, 2013, 7(2): 4-16.
4	LIN C P, CABRERA J, YANG F F, et al. Battery state of health modeling and remaining useful life prediction through time series model[J]. Applied Energy, 2020, 275: doi: 10.1016/j.apenergy.2020.115338.
5	CHEN D, MENG J H, HUANG H Y, et al. An Empirical-data hybrid driven approach for remaining useful life prediction of lithium-ion batteries considering capacity diving[J]. Energy, 2022, 245: doi: 10.1016/j.energy.2022.123222.
6	LOVE C T, VIRJI M B V, ROCHELEAU R E, et al. State-of-health monitoring of 18650 4S packs with a single-point impedance diagnostic[J]. Journal of Power Sources, 2014, 266: 512-519.
7	PRADYUMNA T K, CHO K, KIM M, et al. Capacity estimation of lithium-ion batteries using convolutional neural network and impedance spectra[J]. Journal of Power Electronics, 2022, 22(5): 850-858.
8	PLETT G L. Extended Kalman filtering for battery management systems of LiPB-based HEV battery packs[J]. Journal of Power Sources, 2004, 134(2): 277-292.
9	WANG Y J, ZHANG C B, CHEN Z H. A method for state-of-charge estimation of LiFePO₄ batteries at dynamic currents and temperatures using particle filter[J]. Journal of Power Sources, 2015, 279: 306-311.
10	YAN W Z, ZHANG B, ZHAO G Q, et al. A battery management system with a lebesgue-sampling-based extended Kalman filter[J]. IEEE Transactions on Industrial Electronics, 2019, 66(4): 3227-3236.
11	TULSYAN A, TSAI Y, GOPALUNI R B, et al. State-of-charge estimation in lithium-ion batteries: A particle filter approach[J]. Journal of Power Sources, 2016, 331: 208-223.
12	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.
13	LIN H Y, KANG L Y, XIE D, et al. Online state-of-health estimation of lithium-ion battery based on incremental capacity curve and BP neural network[J]. Batteries, 2022, 8(4): doi: 10.3390/batteries8040029.
14	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.
15	LI X Y, YUAN C G, WANG Z P. State of health estimation for Li-ion battery via partial incremental capacity analysis based on support vector regression[J]. Energy, 2020, 203: doi: 10.1016/j.energy.2020.117852.
16	LI H, PAN D H, CHEN C L P. Intelligent prognostics for battery health monitoring using the mean entropy and relevance vector machine[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2014, 44(7): 851-862.
17	LEWERENZ M, MARONGIU A, WARNECKE A, et al. Differential voltage analysis as a tool for analyzing inhomogeneous aging: A case study for LiFePO₄\|Graphite cylindrical cells[J]. Journal of Power Sources, 2017, 368: 57-67.
18	WEI J W, DONG G Z, CHEN Z H. Remaining useful life prediction and state of health diagnosis for lithium-ion batteries using particle filter and support vector regression[J]. IEEE Transactions on Industrial Electronics, 2018, 65(7): 5634-5643.
19	WANG Z P, YUAN C G, LI X Y. Lithium battery state-of-health estimation via differential thermal voltammetry with Gaussian process regression[J]. IEEE Transactions on Transportation Electrification, 2021, 7(1): 16-25.
20	PAN H H, LÜ Z Q, WANG H M, et al. Novel battery state-of-health online estimation method using multiple health indicators and an extreme learning machine[J]. Energy, 2018, 160: 466-477.
21	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: doi: 10.1016/j.rser.2019.109254.
22	LIU J, CHEN Z Q. Remaining useful life prediction of lithium-ion batteries based on health indicator and Gaussian process regression model[J]. IEEE Access, 2019, 7: 39474-39484.
23	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.
24	李放, 闵永军, 王琛, 等. 基于充电过程的锂电池SOH估计和RUL预测[J]. 储能科学与技术, 2022, 11(10): 3316-3327.
	LI F, MIN Y J, WANG C, et al. State of health estimation and remaining useful life predication of lithium batteries using charging process[J]. Energy Storage Science and Technology, 2022, 11(10): 3316-3327.

HIs	B0005	B0006	B0007	B0018
最高放电温度	-0.9353	-0.8504	-0.7495	-0.6952
平均放电电压	0.9824	0.9652	0.9611	0.9856
放电电压初始骤降值	-0.9607	-0.9160	-0.7439	-0.8853
等压降放电时间	0.9934	0.9928	0.9939	0.9949
最终放电温度	0.5863	0.9348	-0.0218	0.4962
最低电压	-0.4871	-0.4897	-0.3147	0.1176

电池编号	本工作所提健康指标	文献[21]	文献[22]	文献[23]
B0005	0.0072	0.0153	0.1210	0.0290
B0006	0.0196	0.0290	0.2251	0.0452
B0007	0.0210	—	0.2070	0.0259
B0018	0.0186	0.0289	—	0.0342

[1]	陈清炀, 何映晖, 余官定, 刘铭扬, 徐翀, 李振明. 模型与数据双驱动的锂电池状态精准估计[J]. 储能科学与技术, 2023, 12(1): 209-217.
[2]	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.
[3]	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.
[4]	常泽宇, 张之琦, 张晓东, 李丽, 郁亚娟. 基于数据驱动的动力电池健康状态评估平台[J]. 储能科学与技术, 2022, 11(6): 1847-1853.
[5]	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.
[6]	张孝远, 张金浩, 蒋亚俊. 基于改进TCN模型的动力电池健康状态评估[J]. 储能科学与技术, 2022, 11(5): 1617-1626.
[7]	耿萌萌, 范茂松, 杨凯, 赵光金, 谭震, 高飞, 张明杰. 基于EIS和神经网络的退役电池SOH快速估计[J]. 储能科学与技术, 2022, 11(2): 673-678.
[8]	张爽, 许伽宁, 张蓉蓉, 刘宗浩, 王琛淇, 刘若男, 荣明林. 全钒液流电池健康状态（SOH）特性[J]. 储能科学与技术, 2022, 11(12): 4022-4029.
[9]	李放, 闵永军, 王琛, 张涌. 基于充电过程的锂电池SOH估计和RUL预测[J]. 储能科学与技术, 2022, 11(10): 3316-3327.
[10]	周思飞, 李骏, 张道明, 薛浩亮, 王小飞. 基于数理统计方法的锂电池电解液电导率优化设计[J]. 储能科学与技术, 2022, 11(10): 3364-3370.
[11]	孙爱芬, 赤娜. 基于改进的高斯过程回归的SOC估计算法[J]. 储能科学与技术, 2022, 11(1): 253-257.
[12]	王凡, 史永胜, 刘博亲, 左玉洁, 符政, ALI Jamsher. 基于注意力改进BiGRU的锂离子电池健康状态估计[J]. 储能科学与技术, 2021, 10(6): 2326-2333.
[13]	郑永强, 吴越, 张盼盼, 雷博, 郑耀东. 基于多分支拓扑的梯次利用储能系统电池同期退役协同控制策略[J]. 储能科学与技术, 2021, 10(6): 2283-2292.
[14]	冯一峰, 沈佳妮, 车海英, 马紫峰, 贺益君, 谈文, 杨庆亨. 钠离子电池健康状态预测[J]. 储能科学与技术, 2021, 10(4): 1407-1415.
[15]	韩云飞, 谢佳, 蔡涛, 程时杰. 结合高斯过程回归与特征选择的锂离子电池容量估计方法[J]. 储能科学与技术, 2021, 10(4): 1432-1438.