基于热电联合模型和深度学习的锂离子电池温度估计方法

张有兵; 鲍俊挺; 潘红武; 毛苑; 张伟杰; 张志明

doi:10.19799/j.cnki.2095-4239.2025.1109

您当前的位置：

首页 >

文章列表页 >

基于热电联合模型和深度学习的锂离子电池温度估计方法

储能测试与评价 | 更新时间：2026-04-29

- 基于热电联合模型和深度学习的锂离子电池温度估计方法
- Lithium-ion battery temperature estimation method based on thermoelectric combined model and deep learning
- 储能科学与技术 2026年15卷第4期页码：1363-1374
- 作者机构：
  
  1.浙江工业大学信息工程学院，浙江杭州 310014
  2.国网湖州供电公司发展部，浙江湖州 313000
  3.瑞浦兰钧能源股份有限公司，浙江温州 325058
- 作者简介：
  
  张有兵（1971—），男，博士，教授，研究方向为智能电网、分布式发电及新能源优化控制、电动汽车入网、电力系统通信、电能质量监控，E-mail：youbingzhang@zjut.edu.cn；
  张志明，高级工程师，研究方向为新能源汽车动力电池开发及测试，E-mail：zhzhm2@163.com。
- 基金信息：
  
  国家自然科学基金(U22B20116);浙江省科技厅尖兵领雁计划项目(2024C01059)
- DOI：10.19799/j.cnki.2095-4239.2025.1109
  中图分类号： TM 912
- 收稿：2025-12-11，
  
  修回：2026-01-01，
  
  纸质出版：2026-04-28
- 稿件说明：
移动端阅览
张有兵, 鲍俊挺, 潘红武, 等. 基于热电联合模型和深度学习的锂离子电池温度估计方法[J]. 储能科学与技术, 2026, 15(4): 1363-1374.

ZHANG Youbing, BAO Junting, PAN Hongwu, et al. Lithium-ion battery temperature estimation method based on thermoelectric combined model and deep learning[J]. Energy Storage Science and Technology, 2026, 15(4): 1363-1374.
张有兵, 鲍俊挺, 潘红武, 等. 基于热电联合模型和深度学习的锂离子电池温度估计方法[J]. 储能科学与技术, 2026, 15(4): 1363-1374. DOI： 10.19799/j.cnki.2095-4239.2025.1109.

ZHANG Youbing, BAO Junting, PAN Hongwu, et al. Lithium-ion battery temperature estimation method based on thermoelectric combined model and deep learning[J]. Energy Storage Science and Technology, 2026, 15(4): 1363-1374. DOI： 10.19799/j.cnki.2095-4239.2025.1109.

摘要

锂离子电池温度的准确估计作为电池管理系统(battery management system，BMS)的核心技术之一，对电动汽车的安全运行具有重要意义。为此，本研究提出一种结合模型与数据驱动的混合温度预测方法。首先，构建由一阶RC等效电路模型与一阶热模型组成的热电联合模型，并通过自适应遗忘因子递推最小二乘法(adaptive forgetting factor recursive least squares，VFFRLS)进行参数辨识；而后，为克服热等效电路模型在电池空间和材料上的简化导致对变化率较高温度区间的表征受限的问题，设计一种自适应权重物理信息神经网络(adaptive weighted physics-informed neural network，AWPINN)，将联合模型辨识结果作为可学习参数的物理约束，融合了数据驱动能力与模型物理机制。最后，通过VFFRLS与AWPINN模型联合估计得到最终结果，并通过与其他数据驱动模型的对比，证明所提出的温度预测方法的优越性。实验结果表明，在20℃环境下，本方法的平均绝对误差为0.242，均方根误差为0.4069，决定系数达0.9693，性能优于常见模型。在0~40℃范围内，本模型亦保持良好的预测能力，验证了在不同温度条件下的适应性与实用性。

Abstract

Accurate temperature prediction methods for lithium-ion batteries are crucial for timely detection and mitigation of thermal runaway

ensuring battery safety. This study proposes a hybrid temperature-prediction framework that integrates physics-based (model-driven) and neural network (NN; data-driven) methodologies. First

the framework establishes a thermoelectric coupled model integrating a first-order resistor-capacitor electrical model with a first-order thermal model

followed by parameter identification via adaptive forgetting factor recursive least squares (VFFRLS). To address the diminished precision of the equivalent thermal model in regions of rapid temperature changes due to spatial and material simplifications

an adaptiveweighted physics-informed NN (AWPINN) is introduced. This framework integrates data-driven flexibility with model physics by incorporating the output of the thermoelectric coupled model as a learnable parameter constraint. Experimental validation at 20℃ demonstrates that the proposed AWPINN method achieves a mean absolute error of 0.242

a root-mean-square error of 0.4069

and a coefficient of determination of 0.9693

outperforming conventional benchmarks. Further

it maintains excellent predictive capability across a broad operational range of 0—40℃

validating the adaptability and practicality of the model under varying temperature conditions.

关键词

Keywords

references

XIE J, LU Y C. A retrospective on lithium-ion batteries[J]. Nature Communications, 2020, 11: 2499. DOI:10.1038/s41467-020-16259-9.

LARSSON F, MELLANDER B E. Abuse by external heating, overcharge and short circuiting of commercial lithium-ion battery cells[J]. Journal of the Electrochemical Society, 2014, 161(10): A1611-A1617. DOI:10.1149/2.0311410jes.

ZHOU Z Z, LI M Y, ZHOU X D, et al. Investigating thermal runaway triggering mechanism of the prismatic lithium iron phosphate battery under thermal abuse[J]. Renewable Energy, 2024, 220: 119674. DOI:10.1016/j.renene.2023.119674.

XING B B, XIAO F Y, KOROGI Y, et al. Direction-dependent mechanical-electrical-thermal responses of large-format prismatic Li-ion battery under mechanical abuse[J]. Journal of Energy Storage, 2021, 43: 103270. DOI:10.1016/j.est.2021.103270.

RICHARDSON R R, IRELAND P T, HOWEY D A. Battery internal temperature estimation by combined impedance and surface temperature measurement[J]. Journal of Power Sources, 2014, 265: 254-261. DOI:10.1016/j.jpowsour.2014.04.129.

SHEN P, OUYANG M G, LU L G, et al. The co-estimation of state of charge, state of health, and state of function for lithium-ion batteries in electric vehicles[J]. IEEE Transactions on Vehicular Technology, 2018, 67(1): 92-103. DOI:10.1109/TVT.2017.2751613.

HE H W, XIONG R, ZHANG X W, et al. State-of-charge estimation of the lithium-ion battery using an adaptive extended Kalman filter based on an improved thevenin model[J]. IEEE Transactions on Vehicular Technology, 2011, 60(4): 1461-1469. DOI:10.1109/TVT.2011.2132812.

ZHENG F D, JIANG J C, SUN B X, et al. Temperature dependent power capability estimation of lithium-ion batteries for hybrid electric vehicles[J]. Energy, 2016, 113: 64-75. DOI:10.1016/j.energy.2016.06.010.

BAO J T, MAO Y, ZHANG Y B, et al. Critical review of temperature prediction for lithium-ion batteries in electric vehicles[J]. Batteries, 2024, 10(12): DOI:10.3390/batteries10120421.

LIU X F, LI Y C, KANG Y Z, et al. An accurate co-estimation of core temperature and state of charge for lithium-ion batteries with electrothermal model[J]. IEEE Journal of Emerging and Selected Topics in Power Electronics, 2024, 12(1): 231-241. DOI:10.1109/JESTPE.2023.3304754.

ZHANG C, LI K, DENG J. Real-time estimation of battery internal temperature based on a simplified thermoelectric model[J]. Journal of Power Sources, 2016, 302: 146-154. DOI:10.1016/j.jpowsour.2015.10.052.

BAO J T, MAO Y, ZHANG Z M, et al. A data-driven-aided thermoelectric equivalent circuit model for accurate temperature prediction of lithium-ion batteries[J]. International Journal of Energy Research, 2024, 2024(1): 5544635. DOI:10.1155/er/5544635.

HUSSEIN A A. A sensorless surface temperature measurement method for batteries using artificial neural networ ks[C ] //2018 IEEE Energy Conversion Congress and Exposition (ECCE). September 23-27, 2018 , Portland, OR, USA. IEEE, 2018: 3560-3564. DOI:10.1109/ECCE.2018.8557926.

JIANG L, YAN C K, ZHANG X S, et al. Temperature prediction of battery energy storage plant based on EGA-BiLSTM[J]. Energy Reports, 2022, 8: 1009-1018. DOI:10.1016/j.egyr.2022.02.195.

LIU F F, LAN F C, CHEN J Q. Dynamic thermal characteristics of heat pipe via segmented thermal resistance model for electric vehicle battery cooling[J ] . Journal of Power Sources, 2016, 321: 57-70. DOI:10.1016/j.jpowsour.2016.04.108.

AMINI A, ÖZDEMIR T, EKICI Ö, et al. A thermal model for Li-ion batteries operating under dynamic conditions[J]. Applied Thermal Engineering, 2021, 185: 116338. DOI:10.1016/j.applthermaleng. 2020.116338.

CHEN L, ZHANG M, DING Y H, et al. Estimation the internal resistance of lithium-ion-battery using a multi-factor dynamic internal resistance model with an error compensation strategy[J]. Energy Reports, 2021, 7: 3050-3059. DOI:10.1016/j.egyr.2021. 05.027.

ZHANG L J, PENG H, NING Z S, et al. Comparative research on RC equivalent circuit models for lithium-ion batteries of electric vehicles[J]. Applied Sciences, 2017, 7(10): DOI:10.3390/app71 01002.

AZUAJE–BERBECÍ B J, ERTAN H B. A model for the prediction of thermal runaway in lithium-ion batteries[J]. Journal of Energy Storage, 2024, 90: 111831. DOI:10.1016/j.est.2024.111831.

岳永胜, 孙冬, 许爽, 等. 锂离子电池等效电路模型的研究进展[J]. 电池, 2023, 53(6): 682-686.

YUE Y S, SUN D, XU S, et al. Research progress in equivalent circuit model for Li-ion battery[J]. Battery Bimonthly, 2023, 53(6): 682-686.

WANG L M, NIU J Y, ZHAO W, et al. Study on electrochemical and thermal characteristics of lithium-ion battery using the electrochemical-thermal coupled model[J]. International Journal of Energy Research, 2019, 43(6): 2086-2107. DOI:10.1002/er.4410.

刘岸晖, 甘小燕, 何佩芸, 等. 锂离子电池热模型的研究动态[J]. 电源学报, 2019, 17(1): 95-103.

LIU A H, GAN X Y, HE P Y, et al. Progress of research on thermal models of lithium-ion battery[J]. Journal of Power Supply, 2019, 17(1): 95-103.

LIN J Y, LIU X H, LI S, et al. A review on recent progress, challenges and perspective of battery thermal management system[J]. International Journal of Heat and Mass Transfer, 2021, 167: 120834. DOI:10.1016/j.ijheatmasstransfer.2020.120834.

韩莉慧. 基于双线性变换的非线性发展方程的几类精确解的研究[D]. 呼和浩特: 内蒙古工业大学, 2021.HAN L H. Study on some exact solutions of nonlinear evolution equations based on bilinear transformation[D]. Hohhot: Inner Mongolia University of Tehchnology, 2021.

BERNARDI D, PAWLIKOWSKI E, NEWMAN J. A general energy balance for battery systems[J]. Journal of the Electrochemical Society, 1985, 132(1): 5-12. DOI:10.1149/1.2113792.

LIU Z T, LI C G. Recursive least squares for censored regression[J]. IEEE Transactions on Signal Processing, 2017, 65(6): 1565-1579. DOI:10.1109/TSP.2016.2646660.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于单颗粒电化学模型的多种滥用情况下锂电内短路程度评估

基于EEMD-GRU-NN锂离子电池表面温度预测方法研究

基于自适应多层RLS的锂离子电池参数辨识