Transfer learning from synthetic data for open-circuit voltage curve reconstruction and state of health estimation of lithium-ion batteries from partial charging segments
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 , Jacob Hamar , Bastian Mager , Simon Erhard , 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 to , 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.