Transfer learning from synthetic data for open-circuit voltage curve reconstruction and state of health estimation of lithium-ion batteries from partial charging segments

IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Energy and AI Pub Date : 2024-06-06 DOI:10.1016/j.egyai.2024.100382
Tobias Hofmann , Jacob Hamar , Bastian Mager , Simon Erhard , Jan Philipp Schmidt
{"title":"Transfer learning from synthetic data for open-circuit voltage curve reconstruction and state of health estimation of lithium-ion batteries from partial charging segments","authors":"Tobias Hofmann ,&nbsp;Jacob Hamar ,&nbsp;Bastian Mager ,&nbsp;Simon Erhard ,&nbsp;Jan Philipp Schmidt","doi":"10.1016/j.egyai.2024.100382","DOIUrl":null,"url":null,"abstract":"<div><p>Data-driven models for battery state estimation require extensive experimental training data, which may not be available or suitable for specific tasks like open-circuit voltage (OCV) reconstruction and subsequent state of health (SOH) estimation. This study addresses this issue by developing a transfer-learning-based OCV reconstruction model using a temporal convolutional long short-term memory (TCN-LSTM) network trained on synthetic data from an automotive nickel cobalt aluminium oxide (NCA) cell generated through a mechanistic model approach. The data consists of voltage curves at constant temperature, C-rates between <span><math><mrow><mtext>C</mtext><mo>/</mo><mn>30</mn></mrow></math></span> to <span><math><mrow><mn>1</mn><mtext>C</mtext></mrow></math></span>, and a SOH-range from 70<!--> <!-->% to 100<!--> <!-->%. The model is refined via Bayesian optimization and then applied to four use cases with reduced experimental nickel manganese cobalt oxide (NMC) cell training data for higher use cases. The TL models’ performances are compared with models trained solely on experimental data, focusing on different C-rates and voltage windows. The results demonstrate that the OCV reconstruction mean absolute error (MAE) within the average battery electric vehicle (BEV) home charging window (30<!--> <!-->% to 85<!--> <!-->% state of charge (SOC)) is less than 22<!--> <!-->mV for the first three use cases across all C-rates. The SOH estimated from the reconstructed OCV exhibits an mean absolute percentage error (MAPE) below 2.2<!--> <!-->% for these cases. The study further investigates the impact of the source domain on TL by incorporating two additional synthetic datasets, a lithium iron phosphate (LFP) cell and an entirely artificial, non-existing, cell, showing that solely the shifting and scaling of gradient changes in the charging curve suffice to transfer knowledge, even between different cell chemistries. A key limitation with respect to extrapolation capability is identified and evidenced in our fourth use case, where the absence of such comprehensive data hindered the TL process.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":null,"pages":null},"PeriodicalIF":9.6000,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S266654682400048X/pdfft?md5=ea2f1d52a5cbfefe64bb5081c632c13d&pid=1-s2.0-S266654682400048X-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Energy and AI","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S266654682400048X","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Data-driven models for battery state estimation require extensive experimental training data, which may not be available or suitable for specific tasks like open-circuit voltage (OCV) reconstruction and subsequent state of health (SOH) estimation. This study addresses this issue by developing a transfer-learning-based OCV reconstruction model using a temporal convolutional long short-term memory (TCN-LSTM) network trained on synthetic data from an automotive nickel cobalt aluminium oxide (NCA) cell generated through a mechanistic model approach. The data consists of voltage curves at constant temperature, C-rates between C/30 to 1C, and a SOH-range from 70 % to 100 %. The model is refined via Bayesian optimization and then applied to four use cases with reduced experimental nickel manganese cobalt oxide (NMC) cell training data for higher use cases. The TL models’ performances are compared with models trained solely on experimental data, focusing on different C-rates and voltage windows. The results demonstrate that the OCV reconstruction mean absolute error (MAE) within the average battery electric vehicle (BEV) home charging window (30 % to 85 % state of charge (SOC)) is less than 22 mV for the first three use cases across all C-rates. The SOH estimated from the reconstructed OCV exhibits an mean absolute percentage error (MAPE) below 2.2 % for these cases. The study further investigates the impact of the source domain on TL by incorporating two additional synthetic datasets, a lithium iron phosphate (LFP) cell and an entirely artificial, non-existing, cell, showing that solely the shifting and scaling of gradient changes in the charging curve suffice to transfer knowledge, even between different cell chemistries. A key limitation with respect to extrapolation capability is identified and evidenced in our fourth use case, where the absence of such comprehensive data hindered the TL process.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用合成数据进行转移学习,从部分充电片段重建开路电压曲线并评估锂离子电池的健康状况
用于电池状态估计的数据驱动模型需要大量实验训练数据,而这些数据可能无法获得或不适合开路电压(OCV)重建和后续健康状态(SOH)估计等特定任务。为解决这一问题,本研究开发了基于迁移学习的开路电压重构模型,该模型采用时序卷积长短期记忆(TCN-LSTM)网络,通过机理模型方法生成的汽车镍钴铝氧化物(NCA)电池合成数据对其进行训练。数据包括恒温下的电压曲线、C/30 到 1C 之间的 C 率以及 70% 到 100% 的 SOH 范围。通过贝叶斯优化法对该模型进行了改进,然后将其应用于四种使用情况,并在较高使用情况下减少了镍锰钴氧化物(NMC)电池的实验训练数据。将 TL 模型的性能与仅根据实验数据训练的模型进行了比较,重点关注不同的 C 速率和电压窗口。结果表明,在所有 C 速率的前三种使用情况下,平均电池电动汽车 (BEV) 家庭充电窗口(30 % 至 85 % 充电状态 (SOC))内的 OCV 重建平均绝对误差 (MAE) 小于 22 mV。在这些情况下,根据重建的 OCV 估算的 SOH 平均绝对百分比误差 (MAPE) 低于 2.2%。该研究通过纳入两个额外的合成数据集(磷酸铁锂(LFP)电池和完全人造的不存在的电池),进一步研究了源域对 TL 的影响,结果表明,即使在不同的电池化学成分之间,仅靠充电曲线梯度变化的移动和缩放就足以实现知识转移。在我们的第四个使用案例中,我们发现并证明了外推能力方面的一个关键限制,即缺乏此类全面的数据阻碍了 TL 过程。
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 去求助
来源期刊
Energy and AI
Energy and AI Engineering-Engineering (miscellaneous)
CiteScore
16.50
自引率
0.00%
发文量
64
审稿时长
56 days
期刊最新文献
Optimizing catalyst layer composition of PEM fuel cell via machine learning: Insights from in-house experimental data A novel optimization framework for natural gas transportation pipeline networks based on deep reinforcement learning Exploring public attention in the circular economy through topic modelling with twin hyperparameter optimisation Adaptive control systems for dual axis tracker using clear sky index and output power forecasting based on ML in overcast weather conditions Supporting energy policy research with large language models: A case study in wind energy siting ordinances
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1