1.School of Artificial Intelligence,Anhui University,Hefei 230601,Anhui,China
2.School of Electrical Engineering and Automation,Wuhan University,Wuhan 430072,Hubei,China
Show less
文章历史+
Received
Published
2025-06-26
2025-12-24
Issue Date
2026-07-23
PDF (3494K)
摘要
准确估计荷电状态(State of Charge,SOC)是确保锂离子电池可靠运行的基础。针对现有深度学习方法输入特征不足的问题,提出一种基于物理模型和深度学习算法的SOC估计方法。该方法结合卷积神经网络(Convolutional Neural Network,CNN)的局部特征提取能力和双向门控循环单元(Bi-directional Gated Recurrent Unit,BiGRU)的时序序列处理能力,通过引入一阶电阻-电容(Resistor-Capacitor,RC)模型输出的端电压作为输入特征, 与实测电压、电流共同构成神经网络输入,从而提升CNN-BiGRU对复杂动态工况的建模能力。实验结果表明,CNN-BiGRU模型的SOC估计效果良好,对于马里兰大学高级生命工程中心(Center for Advanced Life Cycle Engineering,CALCE)数据集,常温(25 ℃)下其均方根误差为0.16%、平均绝对值误差为0.12%。该模型对不同环境温度和不同老化程度的锂电池均具有较高的预测精度和鲁棒性。
Abstract
Accurate estimation of the State of Charge (SOC) is fundamental to ensure the reliable operation of lithium-ion batteries. To address the issue of insufficient input features in existing deep learning methods, this paper proposes an SOC estimation method based on a combination of a physical model and a deep learning algorithm. This method exploits the local feature extraction capability of the Convolutional Neural Network (CNN) and the temporal sequence processing ability of the Bi-directional Gated Recurrent Unit (BiGRU). By introducing the terminal voltage output from a first-order Resistor-Capacitor (RC) model as an input feature, which is combined with the measured voltage and current to form the neural network input, the modeling capability of the CNN-BiGRU under complex dynamic operating conditions is enhanced. Experimental results demonstrate the good SOC estimation performance of the CNN-BiGRU model. For the Center for Advanced Life Cycle Engineering (CALCE) dataset of University of Maryland, the root mean square error (RMSE) is 0.16% and the mean absolute error (MAE) is 0.12% at room temperature (25 ℃). Furthermore, the proposed model exhibits high prediction accuracy and robustness for lithium-ion batteries under varying ambient temperatures and different degradation levels.
锂离子电池因能量密度高、功率密度高和循环寿命长等优势,已广泛应用于新能源汽车与便携式电子设备等领域[1-3]。然而,锂电池在运行过程中存在过充、过放等风险[4]。使用电池管理系统(Battery Management System,BMS)对电池进行实时监测,可以精准调控充放电过程,确保电池安全运行。电池荷电状态(State of Charge,SOC)是BMS的关键参数,反映电池的剩余电量,但难以直接测量[5-6]。同时,由于电池本身的非线性特性以及不断变化的工作条件,准确估计电池SOC仍然是当前的研究难点[7-8]。
SONGS, LIY W, ZHAOY, et al. Research on SOC estimation based on fragment data of lithium-ion battery[J]. Chinese Journal of Power Sources, 2022, 46(7): 734-738. DOI: 10.3969/j.issn.1002-087X.2022.07.008(Ch ).
ZHOUZ K. Research on multi-state estimation of lithium-ion batteries and sorting method after retirement[D]. Jinan: Shandong University, 2020. DOI: 10.27272/d.cnki.gshdu.2020.005920(Ch ).
JIANX Y, JINJ T, WANGY, et al. Recent progress on layered oxide cathode materials for sodium-ion batteries[J]. Chinese Journal of Engineering, 2022, 44(4): 601-611. DOI: 10.13374/j.issn2095-9389.2021.05.26.001(Ch ).
[7]
GOTZJ D, TEIXEIRAM A S, CORRÊAF C, et al. The influence of overcharging and over-discharging on the capacity degradation of lithium-ion batteries[C]//2024 IEEE Vehicle Power and Propulsion Conference (VPPC). New York: IEEE Press, 2024: 1-6. DOI:10.1109/VPPC63154.2024.10755337 .
LIQ B, ZHANGM H, LUOY, et al. Lithium-ion battery state of charge estimation based on equivalent circuit model[J]. Energy Storage Science and Technology, 2024, 13(9): 3072-3083. DOI: 10.19799/j.cnki.2095-4239.2024.0594(Ch ).
[10]
DEMIRCIO, TASKINS, SCHALTZE, et al. Review of battery state estimation methods for electric vehicles-Part Ⅰ: SOC estimation[J]. Journal of Energy Storage, 2024, 87: 111435. DOI:10.1016/j.est.2024.111435 .
[11]
FANC, O’REGANK, LIL, et al. Frequency domain non-linear characterization and analysis of lithium-ion battery electrodes[J]. Journal of Energy Storage, 2021, 36: 102371. DOI:10.1016/j.est.2021.102371 .
QIANW, ZHAOD Z, GUOX W, et al. State of charge estimation of lithium batteries using adaptive unscented H infinity filter[J]. Energy Storage Science and Technology, 2024, 13(11): 4078-4088. DOI: 10.19799/j.cnki.2095-4239.2024.0434(Ch ).
[14]
LIL, WANGC Y, YANS X, et al. A combination state of charge estimation method for ternary polymer lithium battery considering temperature influence[J]. Journal of Power Sources, 2021, 484: 229204. DOI:10.1016/j.jpowsour.2020.229204 .
[15]
ZHENGF D, XINGY J, JIANGJ C, et al. Influence of different open circuit voltage tests on state of charge online estimation for lithium-ion batteries[J]. Applied Energy, 2016, 183: 513-525. DOI:10.1016/j.apenergy.2016.09.010 .
[16]
SUND M, YUX L, WANGC M, et al. State of charge estimation for lithium-ion battery based on an Intelligent Adaptive Extended Kalman Filter with improved noise estimator[J]. Energy, 2021, 214: 119025. DOI:10.1016/j.energy.2020.119025 .
[17]
CUIZ J, HUW H, ZHANGG Z, et al. An extended Kalman filter based SOC estimation method for Li-ion battery[J]. Energy Reports, 2022, 8: 81-87. DOI:10.1016/j.egyr.2022.02.116 .
[18]
JEONGD, BAE S. Estimating battery state-of-charge with a few target training data by meta-learning[J]. Journal of Power Sources, 2023, 553: 232238. DOI:10.1016/j.jpowsour.2022.232238 .
[19]
CHENJ X, FENGX, JIANGL, et al. State of charge estimation of lithium-ion battery using denoising autoencoder and gated recurrent unit recurrent neural network[J]. Energy, 2021, 227: 120451. DOI:10.1016/j.energy.2021.120451 .
[20]
RENZ, DUC Q, WUZ Y, et al. A comparative study of the influence of different open circuit voltage tests on model-based state of charge estimation for lithium-ion batteries[J]. International Journal of Energy Research, 2021, 45(9): 13692-13711. DOI:10.1002/er.6700 .
LIANGY, CAIM Z, JIANGY F, et al. State of charge estimation of lithium battery based on modified ampere-hour integral method[J/OL]. Journal of Power Supply, 2025: 1-13.
[23]
MOVASSAGHK, RAIHANA, BALASINGAMB, et al. A critical look at coulomb counting approach for state of charge estimation in batteries[J]. Energies, 2021, 14(14): 4074. DOI:10.3390/en14144074 .
[24]
WANGY J, ZHANGX C, LIUK L, et al. System identification and state estimation of a reduced-order electrochemical model for lithium-ion batteries[J]. eTransportation, 2023, 18: 100295. DOI:10.1016/j.etran.2023.100295 .
[25]
CUIX B, LUX J. Order reduction electrochemical mechanism model of lithium-ion battery based on variable parameters[J]. Electrochimica Acta, 2023, 446: 142107. DOI:10.1016/j.electacta.2023.142107 .
[26]
GAOY Z, LIUK L, ZHUC, et al. Co-estimation of state-of-charge and state-of-health for lithium-ion batteries using an enhanced electrochemical model[J]. IEEE Transactions on Industrial Electronics, 2022, 69(3): 2684-2696. DOI:10.1109/TIE.2021.3066946 .
[27]
XUZ C, WANGJ, LUNDP D, et al. Co-estimating the state of charge and health of lithium batteries through combining a minimalist electrochemical model and an equivalent circuit model[J]. Energy, 2022, 240: 122815. DOI:10.1016/j.energy.2021.122815 .
[28]
SOLOMONO O, ZHENGW, CHENJ X, et al. State of charge estimation of Lithium-ion battery using an improved fractional-order extended Kalman filter[J]. Journal of Energy Storage, 2022, 49: 104007. DOI:10.1016/j.est.2022.104007 .
[29]
SHIN, CHENZ W, NIUM, et al. State-of-charge estimation for the lithium-ion battery based on adaptive extended Kalman filter using improved parameter identification[J]. Journal of Energy Storage, 2022, 45: 103518. DOI:10.1016/j.est.2021.103518 .
LIUY Q, LEIW J, LIUQ, et al. Joint state estimation of lithium-ion battery based on dual adaptive extended particle filter[J]. Transactions of China Electrotechnical Society, 2024, 39(2): 607-616. DOI: 10.19595/j.cnki.1000-6753.tces.222357(Ch ).
[32]
CHENY, LIR B, SUNZ Y, et al. SOC estimation of retired lithium-ion batteries for electric vehicle with improved particle filter by H-infinity filter[J]. Energy Reports, 2023, 9: 1937-1947. DOI:10.1016/j.egyr.2023.01.018 .
[33]
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 .
[34]
HARINARAYANANJ, BALAMURUGANP. SOC estimation for a lithium-ion pouch cell using machine learning under different load profiles[J]. Scientific Reports, 2025, 15(1): 18091. DOI:10.1038/s41598-025-02709-1 .
[35]
YANGF F, LIW H, LIC, et al. State-of-charge estimation of lithium-ion batteries based on gated recurrent neural network[J]. Energy, 2019, 175: 66-75. DOI: 10.1016/j.energy.2019.03.059 .
ZHUY F, HEW W, LIJ X, et al. SOC estimation for Li-ion batteries based on Bi-LSTM and Bi-GRU[J]. Energy Storage Science and Technology, 2021, 10(3): 1163-1176. DOI: 10.19799/j.cnki.2095-4239.2021.0051(Ch ).
[38]
VENUGOPALP, VIGNESWARANT, REKAS S. State of charge estimation of lithium batteries in electric vehicles using IndRNN[J]. IETE Journal of Research, 2023, 69(5): 2886-2896. DOI: 10.1080/03772063.2021.1906770 .
[39]
SASIKUMARM, INDUMATHIV, GOPALAKRISHNANR, et al. Implementation of deep learning algorithm to estimate the state of charge (SOC) of lithium ion battery[C]//2025 3rd International Conference on Device Intelligence, Computing and Communication Technologies (DICCT). New York: IEEE Press, 2025: 496-501. DOI:10.1109/DICCT64131.2025.10986646 .
[40]
CUOMOS, DI COLAV S, GIAMPAOLOF, et al. Scientific machine learning through physics-informed neural networks: Where we are and what’s next[J]. Journal of Scientific Computing, 2022, 92(3): 88. DOI:10.1007/s10915-022-01939-z .
[41]
LIZ W, LIUF, YANGW J, et al. A survey of convolutional neural networks: Analysis, applications, and prospects[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(12): 6999-7019. DOI:10.1109/TNNLS.2021.3084827 .
[42]
XINGY J, HEW, PECHTM, et al. State of charge estimation of lithium-ion batteries using the open-circuit voltage at various ambient temperatures[J]. Applied Energy, 2014, 113: 106-115. DOI:10.1016/j.apenergy.2013.07.008 .
SUNP Y, LIJ L, TAOZ F, et al. Research on online parameter identification and SOC estimation of battery under dynamic conditions[J]. Journal of Electronic Measurement and Instrumentation, 2021, 35(1): 10-17. DOI: 10.13382/j.jemi.B2003373(Ch ).