Study of SOC estimation method for lithium-ion battery under ultra-high pulse conditions in high-temperature regions

LU Shimo; SUN Bingxiang; MING Hai; FU Zhicheng; FAN Xinyuan

doi:10.19783/j.cnki.pspc.256008

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Study of SOC estimation method for lithium-ion battery under ultra-high pulse conditions in high-temperature regions

更新时间：2026-07-19

- Study of SOC estimation method for lithium-ion battery under ultra-high pulse conditions in high-temperature regions
- Power System Protection and Control Vol. 54, Issue 14, (2026)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.19783/j.cnki.pspc.256008
  CLC：
- Published：2026
- 稿件说明：
移动端阅览
LU Shimo, SUN Bingxiang, MING Hai, et al. Study of SOC estimation method for lithium-ion battery under ultra-high pulse conditions in high-temperature regions[J]. Power System Protection and Control, 2026, 54(14).
DOI：

LU Shimo, SUN Bingxiang, MING Hai, et al. Study of SOC estimation method for lithium-ion battery under ultra-high pulse conditions in high-temperature regions[J]. Power System Protection and Control, 2026, 54(14). DOI： 10.19783/j.cnki.pspc.256008.

摘要

在超高脉冲工况下，锂离子电池具有单次放电时间短、电流高达数十倍以及温度升高快等特点。针对超高脉冲工况下电池荷电(state of charge

SOC)估计精度不足的问题，提出基于拓展长短期记忆(extended long short-term memory

xLSTM)神经网络模型的电池SOC估计方法。首先，将长短期记忆(long short-term memory

LSTM)神经网络中激活函数改为指数型激活函数，向量形式扩展为矩阵形式，从而提高模型估计能力。然后，在包含高温区的环境温度(25 ℃、35 ℃和45 ℃)下，高功率磷酸铁锂电池以10 s放电周期、50%占空比进行20~50 C脉冲放电实验，所提模型与多种神经网络模型的估计结果进行对比，并对所提模型在高温区的SOC估计性能进行验证。最后，将含有测量误差的低采样频率数据输入至xLSTM神经网络模型，xLSTM神经网络模型的估计结果与安时积分法估计结果进行对比，验证了所提模型的可行性和鲁棒性。

Abstract

Under ultra-high pulse conditions

lithium-ion battery exhibits characteristics such as extremely short discharge duration

discharge currents reaching tens of times the nominal value

and rapid temperature rise. To address inaccurate state of charge (SOC) estimation under such conditions

a SOC estimation method based on an extended long short-term memory (xLSTM) neural network model is proposed. First

the activation function in the long short-term memory (LSTM) neural network is replaced with an exponential function

and the vector form is extended to a matrix formulation

thereby improving the model's estimation performance. Then

pulse discharge experiments are conducted on high-power LiFePO4 batteries under high-temperature conditions (25 ℃

35 ℃

and 45 ℃)

with a 10 s discharge cycle and 50% duty cycle in the 20–50 C range. The proposed method is compared with several neural networks to verify its SOC estimation performance in high temperature regions. Finally

low sampling frequency data with measurement noise are input into the xLSTM model

and its results are compared with those obtained from the ampere-hour integral method

demonstrating the feasibility and robustness of the proposed model.

关键词

Keywords

references

DEMIRCI O, TASKIN S, SCHALTZ E, et al. Review of battery state estimation methods for electric vehicles-part I: SOC estimation[J]. Journal of Energy Storage, 2024, 87.

WANG Limei, SUN Jingling, CAI Yingfeng, et al. A novel OCV curve reconstruction and update method of lithium-ion batteries at different temperatures based on cloud data[J]. Energy, 2023, 268.

LEE J, WON J. Enhanced coulomb counting method for SoC and SoH estimation based on coulombic efficiency[J]. IEEE Access, 2023, 11: 15449-15459.

LIU Xingtao, LI Kun, WU Ji, et al. An extended Kalman filter based data-driven method for state of charge estimation of Li-ion batteries[J]. Journal of Energy Storage, 2021, 40.

ZHANG Hao, SUN Hanlei, KANG Le, et al. Prediction of health level of multiform lithium sulfur batteries based on incremental capacity analysis and an improved LSTM[J]. Protection and Control of Modern Power Systems, 2024, 9(2): 21-31.

RUAN Guanqiang, LIU Zixi, CHENG Jinrun, et al. A deep learning model for predicting the state of energy in lithium-ion batteries based on magnetic field effects[J]. Energy, 2024, 304.

CHEN Guanxu, PENG Weiwen, YANG Fangfang. An LSTM-SA model for SOC estimation of lithium-ion batteries under various temperatures and aging levels[J]. Journal of Energy Storage, 2024, 84.

FU Zhicheng, SUN Bingxiang, GONG Jie, et al. A SOC Estimation method for Li-ion batteries under high-rate pulse conditions based on AO-BPNN model[J]. Space: Science Technology, 2023, 3.

BECK M, PÖPPEL K, SPANRING M, et al. xLSTM: extended long short-term memory[J]. arXiv, 2024.

HU Yuyi, DENG Xiaopeng, YANG Liwei. Interval prediction model for residential daily carbon dioxide emissions based on extended long short-term memory integrating quantile regression and sparse attention[J]. Energy and Buildings, 2025, 333.

COVER T M. Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition[J]. IEEE Transactions on Electronic Computers, 1965, 14(3): 326-334.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

基于MMC的分布式储能系统及其快速SOC均衡控制策略

考虑锂电池多时间尺度效应的参数辨识与SOC估计方法

基于改进自适应卡尔曼滤波算法的锂离子电池荷电状态估计

考虑SOC的混合储能功率分配与自适应虚拟惯性控制

计及SOC影响的电化学储能系统低电压穿越控制策略

Related Author

ZHU Yaheng

LI Hengshuo

ZHANG Wenyan

WANG Yusheng

Related Institution

ZHU Yaheng(1. Institute of New Energy, China University of Petroleum (East China)

PetroChina Planning and Engineering Institute

WANG Jiaxing(1. Institute of New Energy, China University of Petroleum (East China)

PetroChina Planning & Engineering Institute

YU Yue(1. State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources (North China Electric Power University)

AI问答

⁰