Publication:
Deep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised transformer model

Simple item page
dc.citedby18
dc.contributor.authorHannan M.A.en_US
dc.contributor.authorHow D.N.T.en_US
dc.contributor.authorLipu M.S.H.en_US
dc.contributor.authorMansor M.en_US
dc.contributor.authorKer P.J.en_US
dc.contributor.authorDong Z.Y.en_US
dc.contributor.authorSahari K.S.M.en_US
dc.contributor.authorTiong S.K.en_US
dc.contributor.authorMuttaqi K.M.en_US
dc.contributor.authorMahlia T.M.I.en_US
dc.contributor.authorBlaabjerg F.en_US
dc.contributor.authorid7103014445en_US
dc.contributor.authorid57212923888en_US
dc.contributor.authorid36518949700en_US
dc.contributor.authorid6701749037en_US
dc.contributor.authorid37461740800en_US
dc.contributor.authorid57221211074en_US
dc.contributor.authorid57218170038en_US
dc.contributor.authorid15128307800en_US
dc.contributor.authorid55582332500en_US
dc.contributor.authorid56997615100en_US
dc.contributor.authorid7004992352en_US
dc.date.accessioned2023-05-29T09:05:23Z
dc.date.available2023-05-29T09:05:23Z
dc.date.issued2021
dc.descriptionarticle; deep learning; environmental temperature; humanen_US
dc.description.abstractAccurate state of charge (SOC) estimation of lithium-ion (Li-ion) batteries is crucial in prolonging cell lifespan and ensuring its safe operation for electric vehicle applications. In this article, we propose the deep learning-based transformer model trained with self-supervised learning (SSL) for end-to-end SOC estimation without the requirements of feature engineering or adaptive filtering. We demonstrate that with the SSL framework, the proposed deep learning transformer model achieves the lowest root-mean-square-error (RMSE) of 0.90% and a mean-absolute-error (MAE) of 0.44% at constant ambient temperature, and RMSE of 1.19% and a MAE of 0.7% at varying ambient temperature. With SSL, the proposed model can be trained with as few as 5 epochs using only 20% of the total training data and still achieves less than 1.9% RMSE on the test data. Finally, we also demonstrate that the learning weights during the SSL training can be transferred to a new Li-ion cell with different chemistry and still achieve on-par performance compared to the models trained from scratch on the new cell. � 2021, The Author(s).en_US
dc.description.natureFinalen_US
dc.identifier.ArtNo19541
dc.identifier.doi10.1038/s41598-021-98915-8
dc.identifier.issue1
dc.identifier.scopus2-s2.0-85116380133
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85116380133&doi=10.1038%2fs41598-021-98915-8&partnerID=40&md5=80d54626b1e2252e049040c4220484af
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/25877
dc.identifier.volume11
dc.publisherNature Researchen_US
dc.relation.ispartofAll Open Access, Gold, Green
dc.sourceScopus
dc.sourcetitleScientific Reports
dc.titleDeep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised transformer modelen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS