融合MHSA的锂电池SOC估计

高俊东; 马志强; 刘广忱; 宝财吉拉呼; 李宏勋; 刘宇龙

doi:10.19912/j.0254-0096.tynxb.2023-1759

PDF(2725 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (3) : 16-24. DOI: 10.19912/j.0254-0096.tynxb.2023-1759

融合MHSA的锂电池SOC估计

高俊东¹, 马志强^1,2, 刘广忱^2,3, 宝财吉拉呼¹, 李宏勋¹, 刘宇龙¹

作者信息 +

FUSION OF MHSA LITHIUM BATTERY SOC ESTIMATES

Gao Jundong¹, Ma Zhiqiang^1,2, Liu Guangchen^2,3, Bao Caijilahu¹, Li Hongxun¹, Liu Yulong¹

Author information +

文章历史 +

摘要

提出在长短期记忆网络（LSTM）基础上融合多头自注意力机制（LSTM-MHSA）的方法估计动力电池荷电状态（SOC）,将动力电池的电流、电压和温度作为LSTM模型输入,通过带有记忆功能的门控单元选择和遗忘历史数据特征;LSTM处理长序列数据会将所有数据特征同等对待,不能对SOC影响较大的数据特征有效表示,MHSA单元根据数据特性确定特征关注的焦点,提升模型在时序数据中全局和局部的特征提取能力,改进LSTM在对历史数据特征关注度不足和提高模型估计精度;最后在公开数据集上通过对比和泛化实验。结果显示该方法在平均绝对误差上减少0.007,验证在复杂非线性关系的影响下该方法能有效表示长序列数据特征,进而提高SOC估计的精度。

Abstract

A method based on long short-term memory network (LSTM) and multi-head Self-attention mechanism (LSTM-MHSA) was proposed to estimate state of charge (SOC) of power battery. The current, voltage and temperature of the power battery are used as inputs to the LSTM model, and the historical data features are selected and forgotten through a gating unit with memory function. LSTM processes all data features equally in terms of long sequence data and cannot effectively represent data features with greater impacts on SOC. MHSA unit is used to determine the feature focus according to the data characteristics, aiming at enhancing the global and local feature extraction ability of the model in the time series data and improving the LSTM’s insufficient focus on historical data features, therefore improve the model's estimation accuracy. Finally, the comparison and generalization experiments on public datasets indicate that the method reduces the average absolute error by 0.007, which proves that the method can effectively demonstrate long series data features under the influence of complex nonlinear relationships, thus improve the accuracy of SOC estimation.

导出引用

高俊东, 马志强, 刘广忱, 宝财吉拉呼, 李宏勋, 刘宇龙. 融合MHSA的锂电池SOC估计[J]. 太阳能学报. 2025, 46(3): 16-24 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1759

Gao Jundong, Ma Zhiqiang, Liu Guangchen, Bao Caijilahu, Li Hongxun, Liu Yulong. FUSION OF MHSA LITHIUM BATTERY SOC ESTIMATES[J]. Acta Energiae Solaris Sinica. 2025, 46(3): 16-24 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1759

中图分类号： TM912 U469.72

参考文献

[1] 何冰琛, 杨薛明, 王劲松, 等. 基于PCA-GPR的锂离子电池剩余使用寿命预测[J]. 太阳能学报, 2022, 43(5): 484-491.
HE B C, YANG X M, WANG J S, et al.Prediction of remaining useful life of lithium-ion batteries based on PCA-GPR[J]. Acta energiae solaris sinica, 2022, 43(5): 484-491.
[2] 陈海生, 李泓, 马文涛, 等. 2021年中国储能技术研究进展[J]. 储能科学与技术, 2022, 11(3): 1052-1076.
CHEN H S, LI H, MA W T, et al.Research progress of energy storage technology in China in 2021[J]. Energy storage science and technology, 2022, 11(3): 1052-1076.
[3] 许青, 滕婕. 退役动力电池多场景梯次利用优化研究[J]. 太阳能学报, 2023, 44(10): 541-549.
XU Q, TENG J.Multi-scene cascade utilization optimization of retired power battery[J]. Acta energiae solaris sinica, 2023, 44(10): 541-549.
[4] 郑良天, 康丽霞, 黄贤坤, 等. 适应多负载电池储能系统的拓扑结构优化重构方法[J]. 化工进展, 2022, 41(10): 5630-5636.
ZHENG L T, KANG L X, HUANG X K, et al.Optimal reconfiguration method for topology of battery energy storage systems adapting to multiple load demands[J]. Chemical industry and engineering progress, 2022, 41(10): 5630-5636.
[5] 管鸿盛, 钱诚, 徐炳辉, 等. 融合自注意力机制与门控循环单元网络的宽工况锂离子电池SOC估计[J]. 储能科学与技术, 2023, 12(7): 2229-2237.
GUAN H S, QIAN C, XU B H, et al.SAM-GRU-based fusion neural network for SOC estimation in lithium-ion batteries under a wide range of operating conditions[J]. Energy storage science and technology, 2023, 12(7): 2229-2237.
[6] XU W, XU J L, YAN X F.Lithium-ion battery state of charge and parameters joint estimation using cubature Kalman filter and particle filter[J]. Journal of power electronics, 2020, 20(1): 292-307.
[7] ZHENG L F, ZHU J G, LU D D C, et al. Incremental capacity analysis and differential voltage analysis based state of charge and capacity estimation for lithium-ion batteries[J]. Energy, 2018, 150: 759-769.
[8] 赵轩, 李美莹, 余强, 等. 电动汽车动力锂电池状态估计综述[J]. 中国公路学报, 2023, 36(6): 254-283.
ZHAO X, LI M Y, YU Q, et al.State estimation of power lithium batteries for electric vehicles: a review[J]. China journal of highway and transport, 2023, 36(6): 254-283.
[9] ZHANG M Y, FAN X B.Design of battery management system based on improved ampere-hour integration method[J]. International journal of electric and hybrid vehicles, 2022, 14(1/2): 1.
[10] HE Z, LI Y, SUN Y, et al.State-of-charge estimation of lithium ion batteries based on adaptive iterative extended Kalman filter[J]. Journal of energy storage, 2021, 39: 102593.
[11] SHAH A, SHAH K, SHAH C, et al.State of charge, remaining useful life and knee point estimation based on artificial intelligence and machine learning in lithium-ion EV batteries: a comprehensive review[J]. Renewable energy focus, 2022, 42: 146-164.
[12] LIU Z, DANG X J, JING B Q, et al.A novel model-based state of charge estimation for lithium-ion battery using adaptive robust iterative cubature Kalman filter[J]. Electric power systems research, 2019, 177: 105951.
[13] HOW D N T, HANNAN M A, HOSSAIN LIPU M S, et al. State of charge estimation for lithium-ion batteries using model-based and data-driven methods: a review[J]. IEEE access, 2019, 7: 136116-136136.
[14] MOO C S, NG K S, CHEN Y P, et al.State-of-charge estimation with open-circuit-voltage for lead-acid batteries[C]//2007 Power Conversion Conference-Nagoya. Nagoya, Japan, 2007: 758-762.
[15] PANG Z Y, YANG K, SONG Z X, et al.Research on SOC estimation of lithium battery based on electrochemical impedance spectroscopy[C]//2023 6th International Conference on Energy, Electrical and Power Engineering (CEEPE). Guangzhou, China, 2023: 1638-1643.
[16] 高进, 胡红顶, 姚胜华. 基于改进安时积分法的锂离子电池组SOC估算[J]. 湖北汽车工业学院学报, 2022, 36(4): 56-60.
GAO J, HU H D, YAO S H.SOC estimation of lithium-ion battery based on improved ampere hour integral method[J]. Journal of Hubei University of Automotive Technology, 2022, 36(4): 56-60.
[17] WANG Y Q, LI L, DING Q S, et al.Lithium-ion battery SOC estimation based on an improved adaptive extended Kalman filter[C]//2021 IEEE 16th Conference on Industrial Electronics and Applications (ICIEA). Chengdu, China, 2021: 417-421.
[18] SUN B X, WANG L F.The SOC estimation of NIMH battery pack for HEV based on BP neural network[C]//2009 International Workshop on Intelligent Systems and Applications. Wuhan, China, 2009: 1-4.
[19] RUMELHART D E, HINTON G E, WILLIAMS R J.Learning representations by back-propagating errors[J]. Nature, 1986, 323: 533-536.
[20] DONG C, WANG G L.Estimation of power battery SOC based on improved BP neural network[C]//2014 IEEE International Conference on Mechatronics and Automation. Tianjin, China, 2014: 2022-2027.
[21] ASHWINI K P, PRADEEP K S, MANDHAR K A, et al.Recurrent neural network based data-driven SOC estimation in lithium-ion battery[C]//2023 International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE). Ballar, India, 2023: 1-6.
[22] HOCHREITERr S, SCHMIDHUBER J.Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[23] CHUNG J, GULCEHRE C, CHO K, et al.Empirical evaluation of gated recurrent neural networks on sequence modeling[EB/OL]. https://arxiv.org/abs/1412.3555v1.
[24] CHENG A Y, WANG Y, CHENG Z L, et al.State of charge estimation for batteries using recurrent neural networks[C]//2018 Chinese Automation Congress (CAC). Xi’an, China, 2018: 390-395.
[25] 朱元富, 贺文武, 李建兴, 等. 基于Bi-LSTM/Bi-GRU循环神经网络的锂电池SOC估计[J]. 储能科学与技术, 2021, 10(3): 1163-1176.
ZHU Y F, HE W W, LI J 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.
[26] SONG X B, YANG F F, WANG D, et al.Combined CNN-LSTM network for state-of-charge estimation of lithium-ion batteries[J]. IEEE access, 2019, 7: 88894-88902.
[27] LECUN Y, BOTTOU L, BENGIO Y, et al.Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[28] VASWANI A, SHAZEER N, PARMAR N, et al.Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.
[29] KINGMA D P, BA J, HAMMAD M M.Adam: a method for stochastic optimization[EB/OL]. https://arxiv.org/abs/1412.6980v9.
[30] DENG Z W, XU L, LIU H A, et al.Prognostics of battery capacity based on charging data and data-driven methods for on-road vehicles[J]. Applied energy, 2023, 339: 120954.
[31] 裴晟, 陈全世, 林成涛. 基于支持向量回归的电池SOC估计方法研究[J]. 电源技术, 2007, 31(3): 242-243, 252.
PEI S, CHEN Q S, LIN C T.Study on estimating method for battery state of charge based on support vector regression[J]. Chinese journal of power sources, 2007, 31(3): 242-243, 252.
[32] 李超然, 肖飞, 樊亚翔. 基于循环神经网络的锂电池SOC估算方法[J]. 海军工程大学学报, 2019, 31(6): 107-112.
LI C R, XIAO F, FAN Y X.Approach to lithium battery SOC estimation based on recurrent neural network[J]. Journal of Naval University of Engineering, 2019, 31(6): 107-112.
[33] 张艺迪, 孙晖. 基于Bi-LSTM的电动直臂车磷酸铁锂电池SOC估计[J]. 能源工程, 2023, 43(1): 37-42.
ZHANG Y D, SUN H.Estimationof SOC for electric telescopic boom aerial work platform based on Bi-LSTM[J]. Energy engineering, 2023, 43(1): 37-42.
[34] VAPNIK V N.An overview of statistical learning theory[J]. IEEE transactions on neural networks, 1999, 10(5): 988-999.