A deep neural network based battery state of charge: electric vehicle application

IF 2.6 4区 化学 Q3 CHEMISTRY, PHYSICAL
Ionics Pub Date : 2025-06-04 DOI:10.1007/s11581-025-06440-9
Radhia Jebahi, Nadia Chaker, Helmi Aloui
{"title":"A deep neural network based battery state of charge: electric vehicle application","authors":"Radhia Jebahi,&nbsp;Nadia Chaker,&nbsp;Helmi Aloui","doi":"10.1007/s11581-025-06440-9","DOIUrl":null,"url":null,"abstract":"<div><p>Accurate State of Charge (SoC) estimation is critical for the performance, safety, and longevity of Li-ion batteries in electric vehicles (EVs). Traditional model-based approaches, such as equivalent circuit models and Kalman filters, often suffer from computational complexity and sensitivity to parameter variations, while data-driven methods face challenges in generalization due to limited training data or suboptimal algorithm selection. To address these limitations, this study proposes an intelligent SoC estimation process based on a deep neural network, which learns an algebraic expression describing the SoC evolution directly from voltage, current, and temperature measurements. A systematic comparative study evaluates three training algorithms Levenberg–Marquardt, Bayesian Regularization, and Conjugate Gradient under varying data splits to determine the optimal balance between precision and robustness. Results demonstrate that Bayesian Regularization achieves the highest accuracy when trained on 70% of the dataset, with 15% each for validation and testing, reducing the SoC prediction error to below 2%. This outcome not only validates the effectiveness of the proposed data-driven approach but also highlights the importance of algorithm and data split selection in overcoming the generalization challenges of existing methods. The study provides a practical and reliable solution for real-time EV battery management systems.</p></div>","PeriodicalId":599,"journal":{"name":"Ionics","volume":"31 8","pages":"7969 - 7986"},"PeriodicalIF":2.6000,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ionics","FirstCategoryId":"92","ListUrlMain":"https://link.springer.com/article/10.1007/s11581-025-06440-9","RegionNum":4,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0

Abstract

Accurate State of Charge (SoC) estimation is critical for the performance, safety, and longevity of Li-ion batteries in electric vehicles (EVs). Traditional model-based approaches, such as equivalent circuit models and Kalman filters, often suffer from computational complexity and sensitivity to parameter variations, while data-driven methods face challenges in generalization due to limited training data or suboptimal algorithm selection. To address these limitations, this study proposes an intelligent SoC estimation process based on a deep neural network, which learns an algebraic expression describing the SoC evolution directly from voltage, current, and temperature measurements. A systematic comparative study evaluates three training algorithms Levenberg–Marquardt, Bayesian Regularization, and Conjugate Gradient under varying data splits to determine the optimal balance between precision and robustness. Results demonstrate that Bayesian Regularization achieves the highest accuracy when trained on 70% of the dataset, with 15% each for validation and testing, reducing the SoC prediction error to below 2%. This outcome not only validates the effectiveness of the proposed data-driven approach but also highlights the importance of algorithm and data split selection in overcoming the generalization challenges of existing methods. The study provides a practical and reliable solution for real-time EV battery management systems.

Abstract Image

基于深度神经网络的电池充电状态:电动汽车应用
准确的荷电状态(SoC)估算对于电动汽车(ev)锂离子电池的性能、安全性和寿命至关重要。传统的基于模型的方法,如等效电路模型和卡尔曼滤波器,往往存在计算复杂性和对参数变化的敏感性,而数据驱动的方法由于训练数据有限或算法选择不理想而面临泛化挑战。为了解决这些限制,本研究提出了一种基于深度神经网络的智能SoC估计过程,该过程直接从电压、电流和温度测量中学习描述SoC演变的代数表达式。系统比较研究评估了不同数据分割下的Levenberg-Marquardt、Bayesian Regularization和共轭梯度三种训练算法,以确定精度和鲁棒性之间的最佳平衡。结果表明,当对70%的数据集进行训练时,贝叶斯正则化达到了最高的准确率,验证和测试各占15%,将SoC预测误差降低到2%以下。这一结果不仅验证了所提出的数据驱动方法的有效性,而且突出了算法和数据分割选择在克服现有方法泛化挑战方面的重要性。该研究为电动汽车电池实时管理系统提供了一种实用可靠的解决方案。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Ionics
Ionics 化学-电化学
CiteScore
5.30
自引率
7.10%
发文量
427
审稿时长
2.2 months
期刊介绍: Ionics is publishing original results in the fields of science and technology of ionic motion. This includes theoretical, experimental and practical work on electrolytes, electrode, ionic/electronic interfaces, ionic transport aspects of corrosion, galvanic cells, e.g. for thermodynamic and kinetic studies, batteries, fuel cells, sensors and electrochromics. Fast solid ionic conductors are presently providing new opportunities in view of several advantages, in addition to conventional liquid electrolytes.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信