基于模型-数据混合驱动的锂电池荷电状态估计方法

doi:10.6040/j.issn.1672-3961.0.2025.089

摘要/Abstract

摘要： 针对模型驱动方法估算精度不足及数据驱动方法易受训练数据质量影响的问题,提出基于模型-数据混合驱动的锂电池荷电状态(state of charge, SOC)估计方法,通过结合物理模型的先验知识与数据驱动的非线性拟合能力提高SOC估计精度。考虑锂电池的动态特性,利用二阶电阻-电容(resistor-capacitance, RC)等效电路模型,建立电池系统的状态空间方程;采用扩展卡尔曼滤波(extended Kalman filter, EKF)初步估计锂电池SOC;将EKF的估计结果与锂电池的端电流、端电压共同作为Transformer编码器的输入,实现SOC精细化估计。算例分析结果表明,所提方法在多种工况和温度下的平均绝对误差均小于0.7%,能够有效提升SOC辨识方法的结果精度和鲁棒性。

关键词: 荷电状态, 锂电池储能, 扩展卡尔曼滤波, Transformer, 模型-数据混合驱动

Abstract: To address the issues of insufficient estimation accuracy in model-driven methods and susceptibility of data-driven methods to the quality of training data, a model-data hybrid driven estimation method of the state of charge(SOC)for the lithium battery was proposed, which improved the estimation accuracy of SOC by combining the prior knowledge of physical models with the nonlinear fitting capabilities of data-driven methods. Considering the dynamic characteristics of the lithium battery, a second-order resistor-capacitance(RC)equivalent circuit model was used to establish the state-space equations of the battery system. The extended Kalman filter(EKF)was employed to preliminarily estimate the SOC of the lithium battery. The estimation results from the EKF, along with the terminal current and terminal voltage of the lithium battery, were used as inputs to an improved Transformer encoder to achieve a refined estimation of the SOC. The results of the case study showed that the proposed method achieved a mean absolute error of less than 0.7% under various operating conditions and temperatures, which could effectively improve the accuracy and robustness of the SOC identification method.

Key words: state of charge, lithium battery energy storage, extended Kalman filter, Transformer, model-data hybrid driven

中图分类号:

TM71

李玮,任其文,曹永吉,余森,李常刚,阚瑞,刘子琪. 基于模型-数据混合驱动的锂电池荷电状态估计方法[J]. 山东大学学报 (工学版), 2026, 56(3): 156-165.

LI Wei, REN Qiwen, CAO Yongji, YU Sen, LI Changgang, KAN Rui, LIU Ziqi. Model-data hybrid driven estimation method of the state of charge for the lithium battery[J]. Journal of Shandong University(Engineering Science), 2026, 56(3): 156-165.

参考文献

[1] 曹永吉, 张恒旭, 施啸寒, 等. 规模化分布式能源参与大电网安全稳定控制的机制初探[J]. 电力系统自动化, 2021, 45(18): 1-8. CAO Yongji, ZHANG Hengxu, SHI Xiaohan, et al. Preliminary study on participation mechanism of large-scale distributed energy resource in security and stability control of large power grid[J]. Automation of Electric Power Systems, 2021, 45(18): 1-8.
[2] 张恒旭, 马睿聪, 曹永吉, 等. 新型电力系统同步稳定研究综述及展望[J]. 山东大学学报(工学版), 2025, 55(2): 1-15. ZHANG Hengxu, MA Ruicong, CAO Yongji, et al. Review and prospect of research on new power system synchronous stability[J]. Journal of Shandong University(Engineering Science), 2025, 55(2): 1-15.
[3] TIAN Y, LAI R C, LI X Y, et al. A combined method for state-of-charge estimation for lithium-ion batteries using a long short-term memory network and an adaptive cubature Kalman filter[J]. Applied Energy, 2020, 265: 114789.
[4] 邹世豪, 曹永吉, 张恒旭, 等. 考虑碳捕集电厂运行灵活性的网-储联合规划[J]. 高电压技术, 2024, 50(11): 5164-5173. ZOU Shihao, CAO Yongji, ZHANG Hengxu, et al. Joint grid-storage planning considering operational flexibility of carbon capture power plant[J]. High Voltage Engi-neering, 2024, 50(11): 5164-5173.
[5] 申江卫, 高承志, 舒星, 等. 基于迁移模型的锂离子电池宽温度全寿命SOC与可用容量联合估计[J]. 电工技术学报, 2023, 38(11): 3052-3063. SHEN Jiangwei, GAO Chengzhi, SHU Xing, et al. Joint estimation of SOC and usable capacity of lithium-ion battery with wide temperature and full life based on migration model[J]. Transactions of China Electro-technical Society, 2023, 38(11): 3052-3063.
[6] 刘芳, 马杰, 苏卫星, 等. 基于自适应回归扩展卡尔曼滤波的电动汽车动力电池全生命周期的荷电状态估算方法[J]. 电工技术学报, 2020, 35(4): 698-707. LIU Fang, MA Jie, SU Weixing, et al. State of charge estimation method of electric vehicle power battery life cycle based on auto regression extended Kalman filter[J]. Transactions of China Electrotechnical Society, 2020, 35(4): 698-707.
[7] WADI A, ABDEL-HAFEZ M F, HUSSEIN A A, et al. Alleviating dynamic model uncertainty effects for improved battery SOC estimation of EVs in highly dynamic environments[J]. IEEE Transactions on Vehicular Technology, 2021, 70(7): 6554-6566.
[8] 李常刚, 李宝亮, 曹永吉, 等. 人工智能在电力系统潮流计算中的应用综述及展望[J]. 山东大学学报(工学版), 2025, 55(5): 1-17. LI Changgang, LI Baoliang, CAO Yongji, et al. Review and prospect on artificial intelligence application in power system power flow calculation[J]. Journal of Shandong University(Engineering Science), 2025, 55(5): 1-17.
[9] 刘巨, 任羽纶, 易柏年, 等. LSTM-EKF算法实现储能集装箱电芯SOC的优化估计[J]. 电力科学与技术学报, 2024, 39(2): 198-206. LIU Ju, REN Yulun, YI Bonian, et al. Optimal estimation of cell SOC in energy storage container with LSTM-EKF algorithm[J]. Journal of Electric Power Science and Technology, 2024, 39(2): 198-206.
[10] 蔡涛, 张钊诚, 袁奥特, 等. 锂离子电池储能安全管理中的机器学习方法综述[J]. 电力系统保护与控制, 2022, 50(24): 178-187. CAI Tao, ZHANG Zhaocheng, YUAN Aote, et al. Review of machine learning for safety management of li-ion battery energy storage[J]. Power System Protection and Control, 2022, 50(24): 178-187.
[11] 王义军, 左雪. 锂离子电池荷电状态估算方法及其应用场景综述[J]. 电力系统自动化, 2022, 46(14): 193-207. WANG Yijun, ZUO Xue. Review on estimation methods for state of charge of lithium-ion battery and their application scenarios[J]. Automation of Electric Power Systems, 2022, 46(14): 193-207.
[12] YU Q Q, HUANG Y K, TANG A H, et al. OCV-SOC-temperature relationship construction and state of charge estimation for a series-parallel lithium-ion battery pack[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(6): 6362-6371.
[13] XU C, ZHANG E, YAN S, et al. State of charge estimation for liquid metal battery based on an improved sliding mode observer[J]. Journal of Energy Storage, 2022, 45: 103701.
[14] 钱伟, 王亚丰, 郭向伟, 等. 自适应渐消并行扩展H_∞滤波SoC估计[J]. 电机与控制学报, 2025, 29(2): 136-145. QIAN Wei, WANG Yafeng, GUO Xiangwei, et al. State of charge estimation of adaptive fading parallel extended H-infinity filter[J]. Electric Machines and Control, 2025, 29(2): 136-145.
[15] YUN J,CHOI Y,LEE J,et al. State-of-charge estimation method for lithium-ion batteries using extended Kalman filter with adaptive battery parameters[J]. IEEE Access, 2023, 11: 90901-90915.
[16] HOSSAINLIPU M S, HANNAN M A, HUSSAIN A, et al. Data-driven state of charge estimation of lithium-ion batteries: algorithms, implementation factors, limitations and future trends[J]. Journal of Cleaner Production, 2020, 277: 124110.
[17] 李宁, 何复兴, 马文涛, 等. 基于经验模态分解的门控循环单元神经网络的锂离子电池荷电状态估计[J]. 电工技术学报, 2022, 37(17): 4528-4536. LI Ning, HE Fuxing, MA Wentao, et al. State-of-charge estimation of lithium-ion battery based on gated recurrent unit using empirical mode decomposition[J]. Transactions of China Electrotechnical Society, 2022, 37(17): 4528-4536.
[18] 尹春杰, 王亚男, 李鹏飞, 等. 基于LSTM的储能蓄电池SOC与SOH联合在线估计[J]. 电源技术, 2022, 46(5): 541-544. YIN Chunjie, WANG Yanan, LI Pengfei, et al. Joint online estimation of SOC and SOH of energy storage battery pack based on LSTM[J]. Chinese Journal of Power Sources, 2022, 46(5): 541-544.
[19] YI Z H, WANG L W, YANG K T. State of charge estimation for lithium-ion battery using time series Transformer with de-noise de-stationary inception network[J]. Journal of Energy Storage, 2024, 93: 112224.
[20] 耿陈, 彭乔, 孟锦豪, 等. 考虑弛豫过程的锂离子电池电-热-老化耦合建模[J]. 电力自动化设备, 2025, 45(3): 33-39. GENG Chen, PENG Qiao, MENG Jinhao, et al. Coupled electro-thermal-aging modeling for lithium-ion battery considering relaxation process[J]. Electric Power Automation Equipment, 2025, 45(3): 33-39.
[21] 徐俊, 郭喆晨, 谢延敏, 等. 储能锂电池系统综合管理研究进展[J]. 西安交通大学学报, 2024, 58(10): 1-23. XU Jun, GUO Zhechen, XIE Yanmin, et al. Review of research progress in integrated management for energy storage lithium battery systems[J]. Journal of Xi'an Jiaotong University, 2024, 58(10): 1-23.
[22] 董磊, 赖纪东, 苏建徽, 等. 基于IMAFFRLS-EKF的锂电池在线参数辨识和SOC估计方法[J]. 太阳能学报, 2024, 45(6): 66-74. DONG Lei, LAI Jidong, SU Jianhui, et al. Online parameter identification and SOC estimation of lithium battery based on IMAFFRLS-EKF[J]. Acta Energiae Solaris Sinica, 2024, 45(6): 66-74.
[23] HANNAN M A, HOW D N T, HOSSAIN LIPU M S, et al. Deep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised Transformer model[J]. Scientific Reports, 2021, 11: 19541.
[24] KOLLMEYER P, VIDAL C, NAGUIB M, et al. LG 18650HG2 li-ion battery data and example deep neural network xEV SOC estimator script[EB/OL].(2020-03-06)[2025-05-18]. https://data.mendeley.com/datasets/cp3473x7xv/3

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed