Lithium Battery State of Charge Estimation Method Based on Transfer Learning

LI Long; YAN Xumeng; ZHANG Yusheng; FENG Yalin; HU Hongli; DUAN Yujie; CUI Chenhui

doi:10.7652/xjtuxb202311014

您当前的位置：

首页 >

文章列表页 >

Lithium Battery State of Charge Estimation Method Based on Transfer Learning

更新时间：2025-12-08

- Lithium Battery State of Charge Estimation Method Based on Transfer Learning
- Vol. 57, Issue 11, Pages: 142-150(2023)
- 作者机构：
  
  1. 国网陕西省电力有限公司电力科学研究院,西安,710199
  2. 西安交通大学电气工程学院,西安,710049
  3. 国网西安高新供电公司,西安,710076
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202311014
  CLC： TM912
- Online First：10 November 2023，
  
  Published：2023
- 稿件说明：
移动端阅览
LI Long, YAN Xumeng, ZHANG Yusheng, et al. Lithium Battery State of Charge Estimation Method Based on Transfer Learning[J]. 2023, 57(11): 142-150.
DOI：

LI Long, YAN Xumeng, ZHANG Yusheng, et al. Lithium Battery State of Charge Estimation Method Based on Transfer Learning[J]. 2023, 57(11): 142-150. DOI： 10.7652/xjtuxb202311014.

摘要

针对锂电池荷电状态(SOC)估算面临的大型数据集获取困难和训练速度慢的问题

结合深度学习和迁移学习提出一种小样本锂电池荷电状态估算方法。基于卷积-长短期记忆网络(CNN-LSTM)构建深度神经网络结构。在源域上采用K折交叉验证对NASA数据集进行划分

选取SOC估计性能最优的网络

利用目标域内具有多种工况和温度条件的Panasonic小样本数据进行迁移学习。为了提升方法的整体性能

分析了网络超参数对SOC估计结果的影响。实验结果表明:在相同的迭代次数下

该方法在不同的工况下可以较准确地实现小样本电池SOC估计

相较于非小样本迁移学习处理方法的均方根误差降低了47.29%。

Abstract

Aiming at the difficulty of obtaining large data sets and the slow training speed of lithium battery state of charge estimation

a small sample lithium battery state of charge estimation method is proposed by combining deep learning and transfer learning. A deep neural network is constructed based on the convolution-long and short term memory network(CNN-LSTM). In the source domain

K-fold cross-validation is used to divide the NASA data set

select the network with the best SOC estimation performance

and then transfer learning is carried out to Panasonic small data with different temperatures and working conditions in the target domain. In order to improve the overall performance

the influence of network hyperparameters on SOC estimation results is discussed. Compared to non-few-shot transfer learning

the error of this method is reduced by 47.29% under the same epoch.

关键词

Keywords

references

PLETT G L. Extended Kalman filtering for battery management systems of LiPB-based HEV battery packs: part 2 modeling and identification [J]. Journal of Power Sources, 2004, 134(2): 262-276.

麻友良, 陈全世, 齐占宁. 电动汽车用电池SOC定义与检测方法 [J]. 清华大学学报(自然科学版), 2001, 41(11): 95-97, 105.

MA Youliang, CHEN Quanshi, QI Zhanning. Research on the SOC definition and measurement method of batteries used in EVs [J]. Journal of Tsinghua University(Science and Technology), 2001, 41(11): 95-97, 105.

WANG Yujie, TIAN Jiaqiang, SUN Zhendong, et al. A comprehensive review of battery modeling and state estimation approaches for advanced battery management systems [J]. Renewable and Sustainable Energy Reviews, 2020, 131: 110015.

鲁伟, 续丹, 杨晴霞, 等. 锂电池分数阶建模与荷电状态研究 [J]. 西安交通大学学报, 2017, 51(7): 124-129.

LU Wei, XU Dan, YANG Qingxia, et al. Fractional model and state-of-charge of lithium battery [J]. Journal of Xi'an Jiaotong University, 2017, 51(7): 124-129.

GAO Yizhao, LIU Kailong, ZHU Chong, 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.

HANNAN M A, LIPU M S H, HUSSAIN A, et al. A review of lithium-ion battery state of charge estimation and management system in electric vehicle applications: challenges and recommendations [J]. Renewable and Sustainable Energy Reviews, 2017, 78: 834-854.

PLETT G L. Extended Kalman filtering for battery management systems of LiPB-based HEV battery packs:

part 1 Background [J]. Journal of Power Sources, 2004, 134(2): 252-261.

靳博文, 潘天红, 陈山. 基于稳态开路电压的锂离子电池使用程度估算 [J]. 电池, 2019, 49(6): 473-476.

JIN Bowen, PAN Tianhong, CHEN Shan. SOU estimation for li-ion battery based on steady-state open circuit voltage [J]. Battery Bimonthly, 2019, 49(6): 473-476.

丁羿茗, 吕瑞强, 蒋超. 基于EKF算法的神经网络估算锂电池SOC [J]. 电源技术, 2021, 45(10): 1260-1263.

DING Yiming, LÜ Ruiqiang, JIANG Chao. Estimation of lithium battery SOC based on EKF neural network [J]. Chinese Journal of Power Sources, 2021, 45(10): 1260-1263.

程泽, 杨磊, 孙幸勉. 基于自适应平方根无迹卡尔曼滤波算法的锂离子电池SOC和SOH估计 [J]. 中国电机工程学报, 2018, 38(8): 2384-2393.

CHENG Ze, YANG Lei, SUN Xingmian. State of charge and state of health estimation of li-ion batteries based on adaptive square-root unscented Kalman filters [J]. Proceedings of the CSEE, 2018, 38(8): 2384-2393.

赵云飞, 徐俊, 王霄, 等. 双自适应衰减卡尔曼滤波锂电池荷电状态估计 [J]. 西安交通大学学报, 2018, 52(12): 99-105.

ZHAO Yunfei, XU Jun, WANG Xiao, et al. An estimation method for state of charge of lithium-ion batteries using dual adaptive fading extended Kalman filter [J]. Journal of Xi'an Jiaotong University, 2018, 52(12): 99-105.

王霄, 徐俊, 曹秉刚, 等. 小波降噪卡尔曼滤波锂电池荷电状态估计 [J]. 西安交通大学学报, 2017, 51(10): 71-76.

WANG Xiao, XU Jun, CAO Binggang, et al. A Kalman filter SOC estimation method for lithium-ion batteries based on discrete wavelet transform denoising [J]. Journal of Xi'an Jiaotong University, 2017, 51(10): 71-76.

杨帆, 和嘉睿, 陆鸣, 等. 基于BP-UKF算法的锂离子电池SOC估计 [J]. 储能科学与技术, 2023, 12(2): 552-559.

YANG Fan, HE Jiarui, LU Ming, et al. SOC estimation of lithium-ion batteries based on BP-UKF algorithm [J]. Energy Storage Science and Technology, 2023, 12(2): 552-559.

李凌峰, 宫明辉, 乌江. 采用多模模型的锂离子电池荷电状态联合估计算法 [J]. 西安交通大学学报, 2021, 55(1): 78-85.

LI Lingfeng, GONG Minghui, WU Jiang. Joint estimation algorithm for state of charge of li-ion battery with multi-mode model [J]. Journal of Xi'an Jiaotong University, 2021, 55(1): 78-85.

陈颖, 黄凯, 丁恒, 等. 基于子种群自适应思维进化-BP神经网络的锂离子电池SOC估计 [J]. 电源学报, 2022, 20(4): 92-101.

CHEN Ying, HUANG Kai, DING Heng, et al. State-of-charge estimation of lithium-ion battery based on subpopulation adaptive mind evolutionary algorithm-bp neural network [J]. Journal of Power Supply, 2022, 20(4): 92-101.

徐帅, 刘雨辰, 周飞. 基于RNN的锂离子电池SOC估算研究进展 [J]. 电源技术, 2021, 45(2): 263-269.

XU Shuai, LIU Yuchen, ZHOU Fei. Research progress of SOC estimation of lithium ion batteries based on RNN [J]. Chinese Journal of Power Sources, 2021, 45(2): 263-269.

欧明阳, 杨代军, 张存满. 基于循环神经网络的PEMFC寿命预测 [J]. 电池, 2020, 50(2): 123-126.

OU Mingyang, YANG Daijun, ZHANG Cunman. Life prediction of PEMFC based on recurrent neural network [J]. Battery Bimonthly, 2020, 50(2): 123-126.[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.

张帅涛, 蒋品群, 宋树祥, 等. 基于注意力机制和CNN-LSTM融合模型的锂电池SOC预测 [J/OL]. 电源学报[2023-05-19]. http://kns.cnki. net/kcms/detail/12.1420.TM.20220222.1322.005.html.

ZHANG Shuaitao, JIANG Pinqun, SONG Shuxiang, et al. SOC prediction for lithium battery based on the fusion model of attention mechanism and CNN-LSTM [J/OL]. Journal of Power Supply[2023-05-19]. http://kns.cnki. net/kcms/detail/12.1420. TM.20220222.1322.005. html.

李超然, 肖飞, 樊亚翔, 等. 基于深度学习的锂离子电池SOC和SOH联合估算 [J]. 中国电机工程学报, 2021, 41(2): 681-691, 27.

LI Chaoran, XIAO Fei, FAN Yaxiang, et al. Joint estimation of the state of charge and the state of health based on deep learning for lithium-ion batteries [J]. Proceedings of the CSEE, 2021, 41(2): 681-691, 27.

SHEN Sheng, SADOUGHI M, CHEN Xiangyi, et al. A deep learning method for online capacity estimation of lithium-ion batteries [J]. Journal of Energy Storage, 2019, 25: 100817.

陈继斌, 李雯雯, 孙彦玺, 等. 基于卷积-双向长短期记忆网络的电池SOC预测 [J]. 电源技术, 2022, 46(5): 532-535.

CHEN Jibin, LI Wenwen, SUN Yanxi, et al. Battery SOC prediction based on convolution bidirectional long term and short term memory network [J]. Chinese Journal of Power Sources, 2022, 46(5): 532-535.

SHEN Sheng, SADOUGHI M, LI Meng, et al. Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries [J]. Applied Energy, 2020, 260: 114296.

PAN S J, YANG Qiang. A survey on transfer learning [J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345-1359.

赵凯琳, 靳小龙, 王元卓. 小样本学习研究综述 [J]. 软件学报, 2021, 32(2): 349-369.

ZHAO Kailin, JIN Xiaolong, WANG Yuanzhuo. Survey on few-shot learning [J]. Journal of Software, 2021, 32(2): 349-369.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Infrared-Visible Heterogenous Image Matching Based on Intra-Class Transfer Learning

Fault Diagnosis of Rolling Bearings Using Deep Transfer Learning and Adaptive Weighting

Principles, Key Technologies and Emerging Trends of ChatGPT

A Fast Calculation Method for Thermal Flow Fields in Transformer Windings Based on PI-DeepONet

Influence of Structural Parameters on the Summer Operational Characteristics of a Three-Tower-in-One Indirect Air-Cooling System

Related Author

毛远宏

贺占庄

马钟

毕瑞星

王竹平

JIA Feng

LI Shihao

SHEN Jianjun

Related Institution

Xi’an Microelectronics Technology Institute

Key Laboratory of Road Construction Technology and Equipment of Ministry of Education, Chang'an University

Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi'an Jiaotong University

(MOE Key Lab for Intelligent and Network Security, Xi'an Jiaotong University,,)

⁰