Accurate estimation of the State of Charge (SOC) of lithium-ion batteries is crucial for optimizing battery performance, extending service life, and ensuring safe operation. In neural network-based SOC estimation, dynamic neural networks are indispensable, with the Nonlinear AutoRegressive with eXogenous inputs Neural Network (NARXNN) excelling in modeling lithium-ion batteries’ nonlinear time-varying dynamics. To enhance estimation performance, a dual-optimization framework is introduced. First, Forward Orthogonal Least Squares (FOLS) optimizes the NARXNN regression matrix through stepwise orthogonal regression, improving high-speed dynamic adaptability by selecting dominant time-delay terms. Subsequently, Polynomial Chaos (PC) optimizes NARXNN network weights via orthogonal polynomial decomposition, quantifying parameter uncertainties to boost steady-state precision. Under the UDDS, US06, and LA92 driving cycles, the FOLS-PC-NARXNN model achieved MAE values of 0.0255%, 0.0798%, and 0.0479%, respectively. These results represent a significant improvement over the 4.7276%, 1.6783%, and 1.8928% errors from the baseline NARXNN model and also surpass other mainstream methods in comparison. Furthermore, tests conducted at extended sampling intervals of 10, 15, and 30 s confirm the model’s strong robustness and maintained estimation accuracy under varied sampling conditions, collectively demonstrating the effectiveness of the dual-optimization strategy in enhancing SOC estimation.
VengatesanSJayakumarASadasivuniKK.FCEVvs.BEV—a short overview on identifying the key contributors to affordable & clean energy (SDG-7). Energy Strategy Rev2024; 53: 101380.
2.
XuXHanXLuL, et al. Challenges and opportunities toward long-life lithium-ion batteries. J Power Sources2024; 603: 234445.
3.
PramuanjaroenkijAKakaçS.The fuel cell electric vehicles: the highlight review. Int J Hydrogen Energy2023; 48(25): 9401–9425.
4.
NyamathullaSDhanamjayuluC.A review of battery energy storage systems and advanced battery management system for different applications: challenges and recommendations. J Energy Storage2024; 86: 111179.
5.
GuanZYangFZYuTH, et al. An improved multi innovation adaptive robust dual kalman filter algorithm for estimating battery state. Ionics2024; 30(2): 991–1006.
6.
ChenJZhangYWuJ, et al. SOC estimation for lithium-ion battery using the LSTM-RNN with extended input and constrained output. Energy2023; 262: 125375.
7.
DemirciOTaskinSSchaltzE, et al. Review of battery state estimation methods for electric vehicles-part I: SOC estimation. J Energy Storage2024; 87: 111435.
8.
LaiXYiWCuiY, et al. Capacity estimation of lithium-ion cells by combining model-based and data-driven methods based on a sequential extended Kalman filter. Energy2021; 216: 119233.
9.
YuQHuangYTangA, et al. OCV-SOC-temperature relationship construction and state of charge estimation for a series–parallel lithium-ion battery pack. IEEE Trans Intell Transp Syst2023; 24(6): 6362–6371.
10.
ChenGZhouHXuY, et al. A novel SOC-OCV separation and extraction technology suitable for online joint estimation of SOC and SOH in lithium-ion batteries. Energy2025; 326: 136246.
11.
ZhuYXiongYXiaoJ, et al. An improved coulomb counting method based on non-destructive charge and discharge differentiation for the SOC estimation of NCM lithium-ion battery. J Energy Storage2023; 73: 108917.
12.
MohammadiF.Lithium-ion battery State-of-Charge estimation based on an improved Coulomb-Counting algorithm and uncertainty evaluation. J Energy Storage2022; 48: 104061.
13.
ChenMXieXHeC, et al. An integrated framework for ARX model identification and its application to lithium-ion battery. IEEE Trans Instrum Meas2025; 74: 3001414.
14.
FanXFengHYunX, et al. SOC estimation for lithium-ion battery based on AGA-optimized AUKF. J Energy Storage2024; 75: 109689.
15.
HouJLiuJChenF, et al. Robust lithium-ion state-of-charge and battery parameters joint estimation based on an enhanced adaptive unscented Kalman filter. Energy2023; 271: 126998.
16.
YangYDingJShenD, et al. Optimal information fusion-based strong tracking filter for state of charge estimation of lithium-ion batteries. J Electrochem Soc2023; 170(9): 090528.
17.
ZhangJXiaoBNiuG, et al. Joint estimation of state-of-charge and state-of-power for hybrid supercapacitors using fractional-order adaptive unscented Kalman filter. Energy2024; 294: 130942.
18.
HouJJiangYLiuJ, et al. Adaptive linear time-varying parameter-varying modeling of lithium-ion batteries considering aging phenomenon. IEEE Trans Power Electron2025; 40(11): 16853–16869.
RoyAChakrabortyS.Support vector machine in structural reliability analysis: a review. Reliab Eng Syst Saf2023; 233: 109126.
21.
LiuWXuYFengX, et al. Optimal fuzzy logic control of energy storage systems for V/f support in distribution networks considering battery degradation. Int J Electr Power Energy Syst2022; 139: 107867.
22.
ZhaoZH.Improved fuzzy logic control-based energy management strategy for hybrid power system of FC/PV/battery/SC on tourist ship. Int J Hydrogen Energy2022; 47(16): 9719–9734.
23.
HarinarayananJBalamuruganP.SOC estimation for a lithium-ion pouch cell using machine learning under different load profiles. Sci Rep2025; 15: 18091.
24.
HouJJiangJWangS, et al. Recursive identification with multiple forgetting factors for time-varying wireless power transfer systems. IEEE J Emerg Sel Top Power Electron2026; 14: 1350–1361. https://doi.org/10.1109/JESTPE.2025.3598974
25.
ZhangGXiaBWangJ, et al. Intelligent state of charge estimation of battery pack based on particle swarm optimization algorithm improved radical basis function neural network. J Energy Storage2022; 50: 104211.
26.
ShenDDingJHaoT.Elman neural network and Thevenin equivalent circuit model based multi-measurement Kalman filter for SOC estimation. Ionics2024; 30(2): 833–845.
27.
ChenHHouHLiuF, et al. Based on NARXNN-PF state of charge estimation for lithium batteries. Ionics2025; 31(3): 2473–2486.
28.
JiaoMWangDQiuJ.A GRU-RNN based momentum optimized algorithm for SOC estimation. J Power Sources2020; 459: 228051.
29.
YaoKYanXMaoX, et al. A combined improved dung beetle optimization and extreme learning machine framework for precise SOC estimation. Sci Rep2025; 15: 17468.
30.
BaoXChenLLopesAM, et al. Hybrid deep neural network with dimension attention for state-of-health estimation of lithium-ion batteries. Energy2023; 278: 127734.
31.
ZhangCTuLYangZ, et al. A CMMOG-based lithium-battery SOH estimation method using multi-task learning framework. J Energy Storage2025; 107: 114884.
32.
SouidiDChroutaJTelmoudiAJ.A hybrid deep learning approach for SOC estimation in electric vehicle batteries. Int J Dyn Control2025; 13: 280.
33.
ChenLXieSLopesAM, et al. A new SOH estimation method for Lithium-ion batteries based on model-data-fusion. Energy2024; 286: 129597.
34.
Pallavi JoshiSSinghD, et al. Comprehensive review of orthogonal regression and its applications in different domains. Arch Comput Method Eng2022; 29(6): 4027–4047.
35.
GaoXChenCHouH, et al. Response prediction using the PC-NARX model for SDOF systems with degradation and parametric uncertainties. Earthq Eng Eng Vib2022; 21(2): 325–340.
36.
ChenJMaJGanM, et al. Multidirection gradient iterative algorithm: a unified framework for gradient iterative and least squares algorithms. IEEE Trans Automat Contr2021; 67(12): 6770–6777.
37.
GaoXChenMChenC, et al. Real-time hybrid simulation with polynomial chaos NARX modeling for seismic response evaluation of structures subjected to stochastic ground motions. J Struct Eng2022; 148(9): 04022138.
38.
Takyi-AninakwaPWangSZhangH, et al. A NARX network optimized with an adaptive weighted square-root cubature Kalman filter for the dynamic state of charge estimation of lithium-ion batteries. J Energy Storage2023; 68: 107728.
39.
YangJHuangJLiZ, et al. Mitigating velocity errors in least-squares imaging using angle-dependent forward and adjoint Gaussian beam operators. Surv Geophys2021; 42: 1305–1346.
40.
RudinC.Why black box machine learning should be avoided for high-stakes decisions, in brief. Nat Rev Methods Primers2022; 2(1): 81.
