To address the problems of insufficient estimation accuracy, error accumulation, and poor robustness of traditional State of Charge (SOC) estimation models under actual operating conditions, this paper proposes a Closed-loop Nonlinear Autoregressive eXogenous (CL-NARX) neural network model to improve SOC estimation accuracy. The model enhances the fitting capability for complex battery processes by introducing a closed-loop feedback mechanism, effectively suppressing error accumulation, and strengthening robustness by optimizing key hyperparameters. The experimental results show that the model achieves optimal performance, when the training iteration number is 150, the number of neurons in the hidden layer is 10, the input delay layers are 5, and the output delay layers are 2, with estimation errors significantly superior to other neural network models. The maximum error, RMSE, MAE, and MAPE are reduced to 2.58%, 1.41%, 1.36%, and 4.57%, respectively. The model demonstrates high accuracy, effective error handling, and strong robustness, providing reliable technical support for the safe operation of lithium-ion batteries.
GUOZ H, WANGJ X, LIX H, et al. Progress and perspectives of garnet-based solid-state lithium metal batteries: Toward low resistance, high energy density and improved cycling capability[J]. Electrochemical Energy Reviews, 2025, 8(1): 8. DOI:10.1007/s41918-025-00244-1 .
[2]
XIAOY H, GOYALG K, SUJ R, et al. A comprehensive review of electric vehicle recycling: Processes in selective collection, element extraction, and component regeneration[J]. Resources, Conservation and Recycling, 2025, 219: 108309. DOI:10.1016/j.resconrec.2025.108309 .
[3]
NAVINKUMART M, BHARATIRAJAC. Sustainable hydrogen energy fuel cell electric vehicles: A critical review of system components and innovative development recommendations[J]. Renewable and Sustainable Energy Reviews, 2025, 215: 115601. DOI:10.1016/j.rser.2025.115601 .
[4]
ALII M M, KALAMM A, IKRAMA, et al. Energy transition towards electric vehicle technology: Recent advancements[J]. Energy Reports, 2025, 13: 2958-2996. DOI:10.1016/j.egyr.2025.02.029 .
[5]
LIW F, ZHANGF M, GAOZ H, et al. Bioinspired microcapsules toward smart lithium-ion batteries: Concept, mechanism, performance, and criteria[J]. Journal of Energy Chemistry, 2025, 107: 495-511. DOI:10.1016/j.jechem.2025.03.016 .
[6]
SRINIVAASM, LEEY Y, BUSIREDDYM R, et al. Polyimides in next-generation energy devices: Applications in Li-ion batteries to solar cells[J]. Journal of Power Sources, 2025, 641: 236780. DOI:10.1016/j.jpowsour.2025.236780 .
[7]
FURUKAWAK, YAMADAM, ARIYOSHIK. Quantitative analysis of side-reaction rates and capacity fading mechanisms in all-solid-state Li-ion batteries[J]. Journal of Power Sources, 2025, 643: 237001. DOI:10.1016/j.jpowsour.2025.237001 .
[8]
AANNIRM, MOUNAFIA NEL, LOUTOUM, et al. Microwave-assisted process for sustainable recycling of blended cathodes from E-scooter batteries: An integrated optimization approach[J]. Journal of Power Sources, 2025, 643: 237003. DOI:10.1016/j.jpowsour.2025.237003 .
[9]
KIMS, PARKS, KIMD, et al. Closed-loop resynthesis of LiNiCoAlO2 cathode active materials from the industrial leachate of spent li-ion batteries[J]. Chemical Engineering Journal, 2024, 494: 153199. DOI:10.1016/j.cej.2024.153199 .
[10]
SHANGY Z, WANGS S, TANGN H, et al. Research progress in fault detection of battery systems: A review[J]. Journal of Energy Storage, 2024, 98: 113079. DOI:10.1016/j.est.2024.113079 .
[11]
ELALFYD A, GOUDAE, KOTBM F, et al. Comprehensive review of energy storage systems technologies, objectives, challenges, and future trends[J]. Energy Strategy Reviews, 2024, 54: 101482. DOI:10.1016/j.esr.2024.101482 .
[12]
GOK B, YILMAZF C, SERINCANM F, et al. Robust state of charge prediction for lithium-ion batteries in diverse operating environments via machine learning[J]. Measurement, 2025, 253: 117595. DOI:10.1016/j.measurement.2025.117595 .
[13]
HUJ W, LIX D, FANGZ, et al. Estimate state of charge in lithium-ion batteries with unknown data[J]. Applied Energy, 2025, 389: 125736. DOI:10.1016/j.apenergy.2025.125736 .
[14]
WANGC, YANGM J, WANGX, et al. A review of battery SOC estimation based on equivalent circuit models[J]. Journal of Energy Storage, 2025, 110: 115346. DOI:10.1016/j.est.2025.115346 .
[15]
RAHMANIP, CHAKRABORTYS, MELEI, et al. Driving the future: A comprehensive review of automotive battery management system technologies, and future trends[J]. Journal of Power Sources, 2025, 629: 235827. DOI:10.1016/j.jpowsour.2024.235827 .
[16]
ARANDHAKARS, NAKKAJ. State of charge estimation of lithium ion battery for electric vehicle using cutting edge machine learning algorithms: A review[J]. Journal of Energy Storage, 2024, 103: 114281. DOI:10.1016/j.est.2024.114281 .
[17]
WANGZ L, FENGG J, LIUX W, et al. A novel method of parameter identification and state of charge estimation for lithium-ion battery energy storage system[J]. Journal of Energy Storage, 2022, 49: 104124. DOI:10.1016/j.est.2022.104124 .
[18]
SELVARAJV, VAIRAVASUNDARAMI. A Bayesian optimized machine learning approach for accurate state of charge estimation of lithium ion batteries used for electric vehicle application[J]. Journal of Energy Storage, 2024, 86: 111321. DOI:10.1016/j.est.2024.111321 .
[19]
WUF, WANGS L, LIUD L, et al. An improved convolutional neural network-bidirectional gated recurrent unit algorithm for robust state of charge and state of energy estimation of new energy vehicles of lithium-ion batteries[J]. Journal of Energy Storage, 2024, 82: 110574. DOI:10.1016/j.est.2024.110574 .
[20]
WUL X, WEIX Y, LINC S, et al. Battery SOC estimation with physics-constrained BiLSTM under different external pressures and temperatures[J]. Journal of Energy Storage, 2025, 117: 116205. DOI:10.1016/j.est.2025.116205 .
[21]
WASEEMM, LAKSHMIG S, AMIRM, et al. Advancement in battery health monitoring methods for electric vehicles: Battery modelling, state estimation, and Internet-of-things based methods[J]. Journal of Power Sources, 2025, 633: 236414. DOI:10.1016/j.jpowsour.2025.236414 .
[22]
MAL, LIY N, ZHANGT L, et al. Trustworthy battery state of charge estimation enabled by multi-task deep learning[J]. Energy, 2025, 326: 136264. DOI:10.1016/j.energy.2025.136264 .
[23]
TAKYI-ANINAKWAP, MASAHUDUF, ALIT S, et al. Key parameter-enhanced canonical model for lithium-ion battery state-of-charge estimation[J]. Measurement, 2025, 255: 117994. DOI:10.1016/j.measurement.2025.117994 .
[24]
VELUMANID, BANSALA. Temperature estimation in a lithium-ion cell using a machine learning based approach[J]. Applied Thermal Engineering, 2025, 270: 126201. DOI:10.1016/j.applthermaleng.2025.126201 .
[25]
WANGC Y, CUIN X, CUIZ R, et al. Fusion estimation of lithium-ion battery state of charge and state of health considering the effect of temperature[J]. Journal of Energy Storage, 2022, 53: 105075. DOI:10.1016/j.est.2022.105075 .
[26]
OUYANGJ, LINH, HONGY. Whale optimization algorithm BP neural network with chaotic mapping improving for SOC estimation of LMFP battery[J]. Energies, 2024, 17(17): 4300. DOI:10.3390/en17174300 .
[27]
CAIB Z, LIM T, YANGH W, et al. State of charge estimation of lithium-ion battery based on back propagation neural network and AdaBoost algorithm[J]. Energies, 2023, 16(23): 7824. DOI:10.3390/en16237824 .
[28]
OUYANGT C, TUOX Y, GONGY B, et al. Lithium-ion battery SOC estimation under data loss and update stagnation[J]. Energy, 2025, 330: 136969. DOI:10.1016/j.energy.2025.136969 .
[29]
JOSEA, SHRIVASTAVAS. The advancements and research trends in state of charge estimation for lithium-ion batteries over the last two decades: A visualization analysis based on bibliometric data[J]. Journal of Energy Storage, 2025, 123: 116610. DOI:10.1016/j.est.2025.116610 .
[30]
LIP H, AOZ S, HOUJ, et al. Physics-informed mamba neural network with potential knowledge for state-of-charge estimation of lithium-ion batteries[J]. Journal of Energy Storage, 2025, 123: 116546. DOI:10.1016/j.est.2025.116546 .
[31]
ZHANGX Y, ZHANGL P, WUJ H, et al. SOC estimation of lithium-ion batteries using equivalent circuit model and Nyquist plots from EIS data: A machine learning approach[J]. Journal of Electroanalytical Chemistry, 2025, 987: 119093. DOI:10.1016/j.jelechem.2025.119093 .
[32]
TANGT, LIUX T, SUNX, et al. State of charge estimation with representative cells-based hybrid model for lithium-ion battery pack[J]. Journal of Power Sources, 2025, 641: 236911. DOI:10.1016/j.jpowsour.2025.236911 .
[33]
CHIANGC J, VERMAP, TSAIS H. Co-estimation of states and parameters for ultracapacitors of various aging conditions using unscented Kalman filter and recursive least squares[J]. Journal of Energy Storage, 2025, 122: 116588. DOI:10.1016/j.est.2025.116588 .
[34]
LIX, DONGD, HUZ P, et al. A study of adaptive extended Kalman filter with different sliding window lengths for lithium-ion battery state-of-charge estimation[J]. Journal of Energy Storage, 2025, 118: 116276. DOI:10.1016/j.est.2025.116276 .
[35]
WANGS L, DANGQ, GAOZ Q, et al. An innovative square root - untraced Kalman filtering strategy with full-parameter online identification for state of power evaluation of lithium-ion batteries[J]. Journal of Energy Storage, 2024, 104: 114555. DOI:10.1016/j.est.2024.114555 .
[36]
ZHUC Y, WANGS L, YUC M, et al. An improved limited memory-Sage Husa-cubature Kalman filtering algorithm for the state of charge and state of energy co-estimation of lithium-ion batteries based on hysteresis effect-dual polarization model[J]. Energy, 2024, 306: 132465. DOI:10.1016/j.energy.2024.132465 .
[37]
BAGEA N, TAKYI-ANINAKWAP, YANGX Y, et al. Enhanced moving-step unscented transformed-dual extended Kalman filter for accurate SOC estimation of lithium-ion batteries considering temperature uncertainties[J]. Journal of Energy Storage, 2025, 110: 115340. DOI:10.1016/j.est.2025.115340 .
[38]
SOROURIH, OSHNOEIA, CHEY H, et al. A comprehensive review of hybrid battery state of charge estimation: Exploring physics-aware AI-based approaches[J]. Journal of Energy Storage, 2024, 100: 113604. DOI:10.1016/j.est.2024.113604 .
[39]
YUH Q, LUH, ZHANGZ J, et al. A generic fusion framework integrating deep learning and Kalman filter for state of charge estimation of lithium-ion batteries: Analysis and comparison[J]. Journal of Power Sources, 2024, 623: 235493. DOI:10.1016/j.jpowsour.2024.235493 .
[40]
TAKYI-ANINAKWAP, WANGS L, LIUG C, et al. Enhanced extended-input LSTM with an adaptive singular value decomposition UKF for LIB SOC estimation using full-cycle current rate and temperature data[J]. Applied Energy, 2024, 363: 123056. DOI:10.1016/j.apenergy.2024.123056 .
[41]
LIUS Y, LIK, YUJ. Battery pack condition monitoring and characteristic state estimation: Challenges, techniques, and future prospectives[J]. Journal of Energy Storage, 2025, 105: 114446. DOI:10.1016/j.est.2024.114446 .