State of Health Estimation of Lithium-ion Battery Using a CS-SVR Model Based on Evidence Reasoning Rule

doi:10.16183/j.cnki.jsjtu.2021.345

Abstract

Abstract:

The state of health (SOH) estimation accuracy of lithium-ion battery affects the safety and service life of batteries. Aimed at the problem in SOH estimation of lithium-ion battery, a cuckoo search support vector regression (CS-SVR) model based on the evidence reasoning (ER) rule was proposed for SOH estimation. The lithium-ion battery data from NASA Ames Center was used to perform the SOH estimation test. In this method, the average voltage and average temperature of battery discharge cycles were taken as model input, and a fusion belief degree matrix of input data was obtained by the ER rule. The SOH estimation result of the battery was obtained by inputting a fusion belief degree matrix into the SVR model optimized by the CS algorithm. The results show that the CS-SVR algorithm based on the ER rule has a better estimation performance than the five existing models.

Key words: lithium-ion battery, evidence reasoning (ER) rule, cuckoo search (CS), state of health (SOH) estimation, support vector regression (SVR)

CLC Number:

TM912.9

XU Hongdong, GAO Haibo, XU Xiaobin, LIN Zhiguo, SHENG Chenxing. State of Health Estimation of Lithium-ion Battery Using a CS-SVR Model Based on Evidence Reasoning Rule[J]. Journal of Shanghai Jiao Tong University, 2022, 56(4): 413-421.

Figures/Tables 10

Fig.1

Fig.2

Fig.3

Fig.4

Tab.1

Casting results of ( h i ( t ) , I ( t ) )

I(t)	h_i(t)
I(t)	$A 1 i$	…	$A j i$	…	$A J i i$	总计
D₁	a_1,1	…	a_1,_j	…	$a 1, J i$	δ₁
?	?	?	?	?	?	?
D_n	a_n_{, 1}	…	a_n_,_j	…	$a n, J i$	δ_n
?	?	?	?	?	?	?
D_N	a_N_,1	…	a_N_,_j	…	$a N, J i$	δ_N
总计	η₁	…	η_j	…	$η J i$	T_S

Tab.1

Tab.2

Evidence matrix of ( h i ( t ) , I ( t ) )

I(t)	h_i(t)
	$e 1 i$	…	$e j i$	…	$e J i i$
	$A 1 i$	…	$A j i$	…	$A J i i$
D₁	$β 1,1 i$	…	$β 1, j i$	…	$β 1, J i i$
?	?	?	?	?	?
D_n	$β n, 1 i$	…	$β n, j i$	…	$β n, J i i$
?	?	?	?	?	?
D_N	$β N, 1 i$	…	$β N, j i$	…	$β N, J i i$

Tab.2

Fig.5

Fig.6

Fig.7

Tab.3

References 29

[1]	MISYRIS G S, MARINOPOULOS A, DOUKAS D I, et al. On battery state estimation algorithms for electric ship applications[J]. Electric Power Systems Research, 2017, 151: 115-124. doi: 10.1016/j.epsr.2017.05.009 URL
[2]	XU D P, WANG L F, YANG J. Research on Li-ion battery management system [C]//2010 International Conference on Electrical and Control Engineering. Wuhan, China: IEEE, 2010: 4106-4109.
[3]	MA G J, YU C H, HE Z W, et al. Estimation of Li-ion battery SOH using Fletcher-Reeves based ANFIS [C]//2015 IEEE 24th International Symposium on Industrial Electronics. Buzios, Brazil: IEEE, 2015: 827-830.
[4]	LOTFI N, LI J, LANDERS R G, et al. Li-ion battery state of health estimation based on an improved single particle model [C]//2017 American Control Conference. Seattle, USA: IEEE, 2017: 86-91.
[5]	BERECIBAR M, GANDIAGA I, VILLARREAL I, et al. Critical review of state of health estimation methods of Li-ion batteries for real applications[J]. Renewable and Sustainable Energy Reviews, 2016, 56: 572-587. doi: 10.1016/j.rser.2015.11.042 URL
[6]	张新锋, 饶勇翔, 姚蒙蒙. 基于支持向量回归的锂电池健康状态估计[J]. 中北大学学报(自然科学版), 2019, 40(6): 511-516.
	ZHANG Xinfeng, RAO Yongxiang, YAO Mengmeng. Estimation of lithium battery state of health based on support vector regression[J]. Journal of North University of China (Natural Science Edition), 2019, 40(6): 511-516.
[7]	QU J T, LIU F, MA Y X, et al. A neural-network-based method for RUL prediction and SOH moni-toring of lithium-ion battery[J]. IEEE Access, 2019, 7: 87178-87191. doi: 10.1109/ACCESS.2019.2925468 URL
[8]	YANG D, WANG Y J, PAN R, et al. State-of-health estimation for the lithium-ion battery based on support vector regression[J]. Applied Energy, 2018, 227: 273-283. doi: 10.1016/j.apenergy.2017.08.096 URL
[9]	ZENG M M, ZHANG P, YANG Y, et al. SOC and SOH joint estimation of the power batteries based on fuzzy unscented Kalman filtering algorithm[J]. Energies, 2019, 12(16): 3122. doi: 10.3390/en12163122 URL
[10]	CHANG C, WANG Q Y, JIANG J C, et al. Lithium-ion battery state of health estimation using the incremental capacity and wavelet neural networks with genetic algorithm[J]. Journal of Energy Storage, 2021, 38: 102570. doi: 10.1016/j.est.2021.102570 URL
[11]	CHENG G, WANG X Z, HE Y R. Remaining useful life and state of health prediction for lithium batteries based on empirical mode decomposition and a long and short memory neural network[J]. Energy, 2021, 232: 121022. doi: 10.1016/j.energy.2021.121022 URL
[12]	WENG C H, SUN J, PENG H E. Model parametrization and adaptation based on the invariance of support vectors with applications to battery state-of-health monitoring[J]. IEEE Transactions on Vehicular Technology, 2015, 64(9): 3908-3917. doi: 10.1109/TVT.2014.2364554 URL
[13]	刘皓, 胡明昕, 朱一亨, 等. 基于遗传算法和支持向量回归的锂电池健康状态预测[J]. 南京理工大学学报, 2018, 42(3): 329-334.
	LIU Hao, HU Mingxin, ZHU Yiheng, et al. Prediction for state of health of lithium-ion batteries by genetic algorithm and support vector regression[J]. Journal of Nanjing University of Science and Technology, 2018, 42(3): 329-334.
[14]	NG S S Y, XING Y J, TSUI K L. A naive Bayes model for robust remaining useful life prediction of lithium-ion battery[J]. Applied Energy, 2014, 118: 114-123. doi: 10.1016/j.apenergy.2013.12.020 URL
[15]	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. doi: 10.1109/TIE.2017.2782224 URL
[16]	XU X B, JIN Z, YANG J B, et al. Track irregularity fault identification based on evidence reasoning rule [C]//2016 IEEE International Conference on Intelligent Rail Transportation. Birmingham, UK: IEEE, 2016: 298-306.
[17]	XU X B, ZHANG Z, ZHENG J, et al. State estimation method based on evidential reasoning rule [C]//2015 IEEE Advanced Information Technology, Electronic and Automation Control Conference. Chongqing, China: IEEE, 2015: 610-617.
[18]	GAO H B, LIAO L H, HE Y L, et al. Improved control of propeller ventilation using an evidence reasoning rule based Adaboost.M1 approach[J]. Ocean Engineering, 2020, 209: 107329. doi: 10.1016/j.oceaneng.2020.107329 URL
[19]	GHAZVINIAN H, MOUSAVI S F, KARAMI H, et al. Integrated support vector regression and an improved particle swarm optimization-based model for solar radiation prediction[J]. PLoS One, 2019, 14(5): e0217634. doi: 10.1371/journal.pone.0217634 URL
[20]	YANG Y F, ZHANG M H, DAI Y W. A Fuzzy Comprehensive CS-SVR Model-based health status evaluation of radar[J]. PLoS One, 2019, 14(3): e0213833. doi: 10.1371/journal.pone.0213833 URL
[21]	NI K S, NGUYEN T Q. Image superresolution using support vector regression[J]. IEEE Transactions on Image Processing, 2007, 16(6): 1596-1610. doi: 10.1109/TIP.2007.896644 URL
[22]	YANG X S, DEB S. Multiobjective cuckoo search for design optimization[J]. Computers & Operations Research, 2013, 40(6): 1616-1624. doi: 10.1016/j.cor.2011.09.026 URL
[23]	NARTU T R, MATTA M S, KORATANA S, et al. A fuzzified Pareto multiobjective cuckoo search algorithm for power losses minimization incorporating SVC[J]. Soft Computing, 2019, 23(21): 10811-10820. doi: 10.1007/s00500-018-3634-7 URL
[24]	CHENG J T, WANG L, XIONG Y. Ensemble of cuckoo search variants[J]. Computers & Industrial Engineering, 2019, 135: 299-313. doi: 10.1016/j.cie.2019.06.015 URL
[25]	SAHA B, GOEBEL K. Battery data set[R]. California: NASA Ames Prognostics Data Repository, 2007.
[26]	QIN T C, ZENG S K, GUO J B. Robust prognostics for state of health estimation of lithium-ion batteries based on an improved PSO-SVR model[J]. Microelectronics Reliability, 2015, 55(9/10): 1280-1284. doi: 10.1016/j.microrel.2015.06.133 URL
[27]	PEDREGOSA F, VAROQUAUX G, GRAMFORT A, et al. Scikit-learn: Machine learning in Python[J]. Journal of machine Learning Research, 2011, 12: 2825-2830.
[28]	ZHAO F J, ZHOU Z J, HU C H, et al. A new safety assessment method based on evidential reasoning rule with a prewarning function[J]. IEEE Access, 2018, 6: 31862-31871. doi: 10.1109/ACCESS.2018.2815631 URL
[29]	LIAO L H, GAO H B, HE Y L, et al. Fault diagnosis of capacitance aging in DC link capacitors of voltage source inverters using evidence reasoning rule[J]. Mathematical Problems in Engineering, 2020, 2020: 1-12.

电池编号	评估标准	I-SVR	BP-NN	GA-SVR	PSO-SVR	CS-SVR	ER-CS-SVR
B5	MSE	2.7590	1.9259	1.8764	1.8692	1.8655	1.0483
	R²	0.9736	0.9807	0.9820	0.9821	0.9821	0.9900
B7	MSE	3.4116	2.1551	1.3093	1.3034	1.3019	1.1570
	R²	0.9548	0.9730	0.9826	0.9827	0.9827	0.9847