State of health estimation and remaining useful life predication of lithium batteries using charging process

doi:10.19799/j.cnki.2095-4239.2022.0165

Abstract

Abstract:

The state of health (SOH) and the remaining useful life (RUL) of lithium-ion batteries for vehicles are key state parameters. Based on the charging process of electric vehicles, an improved Gaussian process regression (GPR) model for lithium battery SOH estimation and RUL prediction is proposed to achieve accurate estimation of SOH and RUL of the battery to ensure the safe and reliable operation of the vehicle. First, the maximal information coefficient (MIC) and Pearson coefficient are used to screen the multivariate information of the charging process as health factors. Further, the model structure is simplified using principal components analysis (PCA). The Gaussian process regression is then improved using particle swarm optimization and the combined kernel function. Finally, accurate online estimation of SOH and prediction of future RUL and SOH are realized. The validity of the model is verified with the NASA lithium-ion battery data set. This model outperforms other studies in terms of estimation and prediction accuracy. The maximum root mean square error (RMSE) of SOH estimation for test batteries is 0.0148, the maximum RMSE of SOH prediction is 0.0169, and the maximum absolute error of RUL prediction is 1 cycle.

Key words: lithium-ion battery, state of health, remaining useful life, gaussian process regression

CLC Number:

TM 912

Fang LI, Yongjun MIN, Chen WANG, Yong ZHANG. 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.

Figures/Tables 14

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Table 1

Fig. 5

Table 2

Table 3

Hyperparametric of Gaussian process regression model"

电池型号	[a;b]	$[σ f 1 2; l 12; σ f 2 2; l 22; p]$
B0005	[0.0893; 1.6571]	[-2.2319; -4.5958; 1.7447; 4.0460; -2.1070]
B0006	[0.1588; 1.5570]	[0.9150; 1.7572; 3.3170; 0.9777; -4.7147]
B0007	[0.0761; 1.6475]	[4.5495; 2.2757; -4.1064; 3.9239; -0.8211]
B0018	[0.0824; 1.5801]	[-4.2300; -4.0529; 2.3312; 2.9800; -2.4340]

Table 3

Fig. 6

Table 4

Fig. 7

Table 5

Fig. 8

Table 6

References 27

1	SUN Z Y, HAN Y, WANG Z P, et al. Detection of voltage fault in the battery system of electric vehicles using statistical analysis[J]. Applied Energy, 2022, 307: doi:10.1016/j.apenergy.2021.118172.
2	YANG R X, XIONG R, MA S X, et al. Characterization of external short circuit faults in electric vehicle Li-ion battery packs and prediction using artificial neural networks[J]. Applied Energy, 2020, 260: doi:10.1016/j.apenergy.2021.114253.
3	HU J, WEI Z B, HE H W. An online adaptive internal short circuit detection method of lithium-ion battery[J]. Automotive Innovation, 2021, 4(1): 93-102.
4	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.
5	周頔, 宋显华, 卢文斌, 等. 基于日常片段充电数据的锂电池健康状态实时评估方法研究[J]. 中国电机工程学报, 2019, 39(1): 105-111, 325.
	ZHOU D, SONG X H, LU W B, et al. Real-time SOH estimation algorithm for lithium-ion batteries based on daily segment charging data[J]. Proceedings of the CSEE, 2019, 39(1): 105-111, 325.
6	YANG D, WANG Y J, PAN R, et al. A neural network based state-of-health estimation of lithium-ion battery in electric vehicles[J]. Energy Procedia, 2017, 105: 2059-2064.
7	WEI M, YE M, WANG Q, et al. State-of-health estimation and remaining useful life prediction of lithium-ion batteries based on extreme learning machine[J]. Journal of Physics: Conference Series, 2021, 1983(1): 012058.
8	SHEN S, SADOUGHI M, CHEN X Y, et al. A deep learning method for online capacity estimation of lithium-ion batteries[J]. Journal of Energy Storage, 2019, 25: doi:10.1016/j.est.2019.100817
9	王英楷, 张红, 王星辉. 基于1DCNN-LSTM的锂离子电池SOH预测[J]. 储能科学与技术, 2022, 11(1): 240-245.
	WANG Y K, ZHANG H, WANG X H. Hybrid 1DCNN-LSTM model for predicting lithium ion battery state of health[J]. Energy Storage Science and Technology, 2022, 11(1): 240-245.
10	FAN Y X, XIAO F, LI C R, et al. A novel deep learning framework for state of health estimation of lithium-ion battery[J]. Journal of Energy Storage, 2020, 32: 25: doi:10.1016/j.est.2020.101741.
11	TSANG K M, CHAN W L. State of health detection for Lithium ion batteries in photovoltaic system[J]. Energy Conversion and Management, 2013, 65: 7-12.
12	ZHANG J A, WANG P, GONG Q R, et al. SOH estimation of lithium-ion batteries based on least squares support vector machine error compensation model[J]. Journal of Power Electronics, 2021, 21(11): 1712-1723.
13	WANG Z P, MA J, ZHANG L. State-of-health estimation for lithium-ion batteries based on the multi-island genetic algorithm and the Gaussian process regression[J]. IEEE Access, 5: 21286-21295.
14	杨胜杰, 罗冰洋, 王菁, 等. 基于差分热伏安法的锂离子电池SOH诊断[J]. 电源技术, 2021, 45(11): 1427-1430.
	YANG S J, LUO B Y, WANG J, et al. State of health diagnosis for lithiumion batteries based on differential thermal voltammetry[J]. Chinese Journal of Power Sources, 2021, 45(11): 1427-1430.
15	HU X S, JIANG J C, CAO D P, et al. Battery health prognosis for electric vehicles using sample entropy and sparse Bayesian predictive modeling[J]. IEEE Transactions on Industrial Electronics, 2016, 63(4): 2645-2656.
16	HUANG Y S, QIN L L, WU G. State of health estimation based on constant current charging profiles[C]//2021 40th Chinese Control Conference (CCC). Shanghai, China. IEEE, 2021: 5899-5904.
17	王凡, 史永胜, 刘博亲, 等. 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.
	WANG F, SHI Y S, LIU B Q, et al. Health state estimation of lithium-ion batteries based on attention augmented BiGRU[J]. Energy Storage Science and Technology, 2021, 10(6): 2326-2333.
18	LIU W, XU Y, FENG X. A hierarchical and flexible data-driven method for online state-of-health estimation of Li-ion battery[J]. IEEE Transactions on Vehicular Technology, 2020, 69(12): 14739-14748.
19	SON S, JEONG S, KWAK E, et al. Integrated framework for SOH estimation of lithium-ion batteries using multiphysics features[J]. Energy, 2022, 238: 25: doi:10.1016/j.energy.2021.121712.
20	QU J T, LIU F, MA Y X, et al. A neural-network-based method for RUL prediction and SOH monitoring of lithium-ion battery[J]. IEEE Access, 2019, 7: 87178-87191.
21	RESHEF D N, RESHEF Y A, FINUCANE H K, et al. Detecting novel associations in large data sets[J]. Science, 2011, 334(6062): 1518-1524.
22	KOBAYASHI Y, MIYASHIRO H, YAMAZAKI A, et al. Unexpected capacity fade and recovery mechanism of LiFePO₄/graphite cells for grid operation[J]. Journal of Power Sources, 2020, 449: doi:10.1016/j.jpowsour.2019.227502.
23	BANERJEE A, DUNSON D B, TOKDAR S T. Efficient Gaussian process regression for large datasets[J]. Biometrika, 2012, 100(1): 75-89.
24	佘承其, 张照生, 刘鹏, 等. 大数据分析技术在新能源汽车行业的应用综述——基于新能源汽车运行大数据[J]. 机械工程学报, 2019, 55(20): 3-16.
	SHE C Q, ZHANG Z S, LIU P, et al. Overview of the application of big data analysis technology in new energy vehicle industry: Based on operating big data of new energy vehicle[J]. Journal of Mechanical Engineering, 2019, 55(20): 3-16.
25	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.
26	刘健, 陈自强, 黄德扬, 等. 基于等压差充电时间的锂离子电池寿命预测[J]. 上海交通大学学报, 2019, 53(9): 1058-1065.
	LIU J, CHEN Z Q, HUANG D Y, et al. Remaining useful life prediction for lithium-ion batteries based on time interval of equal charging voltage difference[J]. Journal of Shanghai Jiao Tong University, 2019, 53(9): 1058-1065.
27	XIANG M, HE Y G, ZHANG H, et al. State-of-health prognosis for lithium-ion batteries considering the limitations in measurements via maximal information entropy and collective sparse variational Gaussian process[J]. IEEE Access, 2020, 8: 188199-188217.

电池型号	相关性分析方法	T_∆_V	Temp _t_-max	T_CC	V₁₀₀₀	S_V	T_CV	T_CC/T_CV	Temp_max	Temp_average
B0005	Pearson	0.9961	0.9958	0.9963	-0.9820	0.9965	-0.9115	-0.9822	-0.5038	0.0119
B0005	MIC	0.9727	0.9672	0.9727	0.9702	0.9727	0.8037	0.9422	0.6004	0.3803
B0006	Pearson	0.9899	0.9904	0.9906	-0.9788	0.9907	-0.9372	-0.9523	0.3451	0.2543
B0006	MIC	0.9727	0.9591	0.9727	0.9727	0.9727	0.8005	0.9349	0.3811	0.4040
B0007	Pearson	0.9890	0.9923	0.9929	-0.9680	0.9927	-0.8828	-0.9799	-0.4357	0.0948
B0007	MIC	0.9727	0.9807	0.9807	0.9546	0.9727	0.6998	0.8926	0.6124	0.4110
B0018	Pearson	0.9854	0.9876	0.9803	-0.9727	0.9819	-0.4089	-0.8854	-0.0236	0.1611
B0018	MIC	0.9791	0.9697	0.9697	0.9791	0.9697	0.7087	0.9632	0.1847	0.1197

成分	特征值
F₁	4.9749
F₂	0.0236
F₃	0.0009
F₃	0.0005
F₅	0.0001

电池型号	PE-GPR		NN-GPR		NN+PE-GPR		PSO- NN+PE-GPR
电池型号	MAPE/%	RMSE	MAPE/%	RMSE	MAPE/%	RMSE	MAPE/%	RMSE
B0005	8.4889	0.0767	3.2967	0.0290	2.9605	0.0220	0.6426	0.0070
B0006	7.5277	0.0554	5.9013	0.0452	2.5350	0.0197	1.0376	0.0092
B0007	3.9387	0.0384	3.4364	0.0259	2.5054	0.0204	0.5022	0.0051
B0018	5.6665	0.0416	3.4991	0.0324	1.8643	0.0200	0.9604	0.0148

电池型号	PSO-NN+PE-GPR		文献[26]		RVM
电池型号	MAPE/%	RMSE	MAPE/%	RMSE	MAPE/%	RMSE
B0005	0.6426	0.0070	0.6000	0.0120	2.9019	0.0263
B0006	1.0376	0.0092	1.2000	0.0190	3.4733	0.0282
B0007	0.5022	0.0051	—	—	3.6751	0.0366
B0018	0.9604	0.0148	—	—	4.0011	0.0373

电池型号	GPR			文献[26]	文献[27]	二次函数拟合
电池型号	SOH预测 MAPE/%	SOH预测 RMSE	RUL绝对误差	RUL绝对误差	SOH预测 RMSE	SOH预测 MAPE/%	SOH预测RMSE	RUL绝对误差
B0005	0.9393	0.0086	0	1	0.0155	15.5748	0.1230	16
B0006	1.4152	0.0115	0	5	0.0281	4.8294	0.0329	6
B0007	0.7030	0.0064	1	—	0.0148	11.8410	0.0987	18
B0018	1.8957	0.0169	1	—	0.0143	4.9786	0.0446	2