State of Health (SOH) of lithium batteries plays a pivotal role in ensuring that electric vehicles operate consistently, reliably, and efficiently. In the actual working conditions, there are a variety of environmental factors to affect the error caused by inaccurate measurement when collecting data. The appearance of measurement error will lead to inaccurate prediction accuracy. To solve the problem of inaccurate SOH predictions, kernel extreme learning machine (KELM) optimized by the Bat Algorithm (BA), adding grey number theory, is proposed. Four types of battery datasets provided by the University of Oxford (OXFORD), Center for Advanced Life Cycle Engineering (CALCE), and National Aeronautics and Space Administration (NASA) are utilized as the objective. Multiple appropriate health characteristics are extracted as inputs for the predictive model. In order to predict the SOH range value of lithium batteries, it is necessary to use the grey number theory to describe the parameters in a range or interval based on the uncertainty of the parameters. The estimated range of SOH of lithium battery obtained by this method provides a new idea for lithium battery early warning system to set the upper and lower limit.
ZhouLLaiXLiB, et al. State estimation models of lithium-ion batteries for battery management system: status, challenges, and future trends. Batteries2023; 9: 131.
2.
HouacheMYimCKarkarZ, et al. On the current and future outlook of battery chemistries for electric vehicles—mini review. Batteries2022; 8: 70.
3.
LiYLiuKFoleyA, et al. Data-driven health estimation and lifetime prediction of lithium-ion batteries: a review. Renew Sustain Energy Rev2019; 113: 109254.
MaCDuHLiuJ, et al. High-temperature stability of dielectric and energy-storage properties of weakly-coupled relaxor (1-x) BaTiO3−xBi(Y1/3Ti1/2) O3 ceramics. Ceram Int2021; 47: 25029–25036.
6.
LiDWangLDuanC, et al. Temperature prediction of lithium-ion batteries based on electrochemical impedance spectrum: a review. Int J Energy Res2022; 46: 10372–10388.
7.
LiC.A unified GPR model based on transfer learning for SOH prediction of lithium-ion batteries. J Process Control2024; 144: 103337.
8.
JiangBZhuJWangX, et al. A comparative study of different features extracted from electrochemical impedance spectroscopy in state of health estimation for lithium-ion batteries. Appl Energy2022; 322: 119502.
9.
ShuXShenJLiG, et al. A flexible state-of-health prediction scheme for lithium-ion battery packs with long short-term memory network and transfer learning. IEEE Trans Transp Electrif2021; 7(4): 2238–2248.
10.
WangDQ.Key-term separation based hierarchical gradient approach for NN based Hammerstein battery model. Appl Math Lett2024; 157: 109207.
11.
JiangSSongZ.A review on the state of health estimation methods of lead-acid batteries. J Power Sources2022; 517: 230710.
12.
YamadaKYamadaYOtsuK, et al. The intelligent automotive battery, “CYBOX®”. J Power Sources2008; 185: 1478–1483.
13.
JiangSDSongZX.Estimating the state of health of lithium-ion batteries with a high discharge rate through impedance. Energies2021; 14: 4833.
14.
TangXGaoFLiuK, et al. A balancing current ratio based state-of-health estimation solution for lithium-ion battery pack. IEEE Trans Ind Electron2022; 69: 8055–8065.
15.
TianJXiongRYuQ.Fractional-order model-based incremental capacity analysis for degradation state recognition of lithium-ion batteries. IEEE Trans Ind Electron2019; 66: 1576–1584.
16.
YangDZhangXPanR, et al. A novel Gaussian process regression model for state-of-health estimation of lithium-ion battery using charging curve. J Power Sources2018; 384: 387–395.
17.
NgSXingYTsuiK.A naive Bayes model for robust remaining useful life prediction of lithium-ion battery. Appl Energy2014; 118: 114–123.
18.
LinHLiangTChenS.Estimation of battery state of health using probabilistic neural network. IEEE Trans Industr Inform2019; 9: 679–685.
19.
WengCSunJPengH.Model parametrization and adaptation based on the invariance of support vectors with applications to battery state-of-health monitoring. IEEE Trans Veh Technol2015; 64: 3908–3917.
20.
ZhangLZhangJGaoT, et al. Improved LSTM based state of health estimation using random segments of the charging curves for lithium-ion batteries. J Energy Storage2023; 74: 109370.
21.
ZhangCLTuLYangZ, et al. A CMMOG-based lithium-battery SOH estimation method using multi-task learning framework. J Energy Storage2025; 107: 114884.
22.
ChenLPXieSQLopesAM, et al. A vision transformer-based deep neural network for state of health estimation of lithium-ion batteries. Int J Electr Power Energy Syst2023; 152: 109233.
23.
WangYXZhaoSYWangSQ, et al. Enhanced vision-transformer integrating with semi-supervised transfer learning for state of health and remaining useful life estimation of lithium-ion batteries. Energy AI2024; 17: 100405.
24.
YeLHPengDHXueDB, et al. Co-estimation of lithium-ion battery state-of-charge and state-of-health based on fractional-order model. J Energy Storage2023; 65: 107225.
25.
ChenLPXieSQLopesAM, et al. A new SOH estimation method for Lithium-ion batteries based on model-data-fusion. Energy2024; 286: 129597.
26.
GuiXNDuJRWangQL, et al. Multi-modal data information alignment based SOH estimation for lithium-ion batteries using a local–global parallel CNN-Transformer Network. J Energy Storage2025; 129: 117178.
27.
HuangJHeTZhuWL, et al. A lithium-ion battery SOH estimation method based on temporal pattern attention mechanism and CNN-LSTM model. Comput Electr Eng2025; 122: 109930.
28.
GuoHYuLRenY, et al. A dual dimensionality reduction and feature weighting integration transfer learning method for lithium-ion battery state of health estimation. J Energy Storage2025; 130: 117475.
29.
YiZChenZYinK, et al. Sensing as the key to the safety and sustainability of new energy storage devices. Prot Control Mod Power Syst2023; 8: 1–22.
30.
LinCSTuoXGWuLX, et al. Physics-informed machine learning for accurate SOH estimation of lithium-ion batteries considering various temperatures and operating conditions. Energy2025; 318: 134937.
31.
HuangGZhuQSiewC.Extreme learning machine: theory and applications. Neurocomputing2006; 70: 489–501.
32.
ChenCLiWSuH, et al. Spectral-spatial classification of hyperspectral image based on kernel extreme learning machine. Remote Sens2014; 6: 5795–5814.
33.
ChenQWeiHRashidM, et al. Kernel extreme learning machine based hierarchical machine learning for multi-type and concurrent fault diagnosis. Measurement2021; 184: 109923.
34.
HuangG.An insight into extreme learning machines: random neurons, random features and kernels. Cogn Comput2014; 6: 376–390.
35.
HuangGHuangGSongS, et al. Trends in extreme learning machines: a review. Neural Netw2015; 61: 32–48.
36.
HuangGZhouHDingX, et al. Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern B Cybern2012; 42: 513–529.
37.
ChawlaMDuhanM.Bat algorithm: a survey of the state-of-the-art. Appl Artif Intell2015; 29: 617–634.
38.
AgarwalTKumarV.A systematic review on Bat algorithm: theoretical foundation, variants, and applications. Arch Comput Methods Eng2022; 29: 2707–2736.
DengJ.Control problems of grey systems. Syst Control Lett1982; 1: 288–294.
41.
RaoSLiuX.Universal grey system theory for analysis of uncertain structural systems. AIAA J2017; 55: 3966–3979.
42.
LiuSLiuY.Grey information: theory and practical applications. London: Springer, 2006.
43.
LiuSForrestJ.Advances in grey systems theory and its applications. In: 2007 IEEE international conference on grey systems and intelligent services, Nanjing, China, 18–20 November 2007, pp.1–6. New York: IEEE.
44.
BadiIAAbdulshahedAMShetwanA, et al. A grey-based assessment approach to the site selection of a desalination plant in Libya. Grey Syst Theory Appl2018; 8(3): 366–379.
45.
MahmoudiADengXPJavedSA, et al. Sustainable supplier selection in megaprojects: grey ordinal priority approach. Bus Strategy Environ2021; 30: 318–339.
46.
ChenJGaoXRongJ.Enhance the uncertainty modeling ability of fuzzy grey cognitive maps by general grey number. IEEE Access2020; 8: 163844–163856.
47.
AlazwariMARaoSS.Uncertainty analysis of large structures using universal grey number theory. Appl Math Comput2022; 416: 126735.
48.
FangPYWangDLiJ, et al. An interval uncertainty modeling method based on information granulation and improved multidimensional parallelepiped. Comput Methods Appl Mech Eng2024; 432(8): 117424.
49.
ZhengYFGuYGaoL, et al. A new structural uncertainty analysis method based on polynomial expansions. Appl Math Comput2022; 427: 127122.
50.
LiuSYangYForrestJ.Grey data analysis: computational risk management. Singapore: Springer, 2017.
51.
ZhangSXuKJowT.Study of the charging process of a LiCoO2-based Li-ion battery. J Power Sources2006; 160: 1349–1354.
