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

Abstract Accurate 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 (...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: M. A. Hannan, D. N. T. How, M. S. Hossain Lipu, M. Mansor, Pin Jern Ker, Z. Y. Dong, K. S. M. Sahari, S. K. Tiong, K. M. Muttaqi, T. M. Indra Mahlia, F. Blaabjerg
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/37125291cee749d5afdfff954166db3d
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:37125291cee749d5afdfff954166db3d
record_format dspace
spelling oai:doaj.org-article:37125291cee749d5afdfff954166db3d2021-12-02T17:17:40ZDeep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised transformer model10.1038/s41598-021-98915-82045-2322https://doaj.org/article/37125291cee749d5afdfff954166db3d2021-10-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-98915-8https://doaj.org/toc/2045-2322Abstract Accurate 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.M. A. HannanD. N. T. HowM. S. Hossain LipuM. MansorPin Jern KerZ. Y. DongK. S. M. SahariS. K. TiongK. M. MuttaqiT. M. Indra MahliaF. BlaabjergNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
M. A. Hannan
D. N. T. How
M. S. Hossain Lipu
M. Mansor
Pin Jern Ker
Z. Y. Dong
K. S. M. Sahari
S. K. Tiong
K. M. Muttaqi
T. M. Indra Mahlia
F. Blaabjerg
Deep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised transformer model
description Abstract Accurate 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.
format article
author M. A. Hannan
D. N. T. How
M. S. Hossain Lipu
M. Mansor
Pin Jern Ker
Z. Y. Dong
K. S. M. Sahari
S. K. Tiong
K. M. Muttaqi
T. M. Indra Mahlia
F. Blaabjerg
author_facet M. A. Hannan
D. N. T. How
M. S. Hossain Lipu
M. Mansor
Pin Jern Ker
Z. Y. Dong
K. S. M. Sahari
S. K. Tiong
K. M. Muttaqi
T. M. Indra Mahlia
F. Blaabjerg
author_sort M. A. Hannan
title Deep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised transformer model
title_short Deep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised transformer model
title_full Deep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised transformer model
title_fullStr Deep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised transformer model
title_full_unstemmed Deep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised transformer model
title_sort deep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised transformer model
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/37125291cee749d5afdfff954166db3d
work_keys_str_mv AT mahannan deeplearningapproachtowardsaccuratestateofchargeestimationforlithiumionbatteriesusingselfsupervisedtransformermodel
AT dnthow deeplearningapproachtowardsaccuratestateofchargeestimationforlithiumionbatteriesusingselfsupervisedtransformermodel
AT mshossainlipu deeplearningapproachtowardsaccuratestateofchargeestimationforlithiumionbatteriesusingselfsupervisedtransformermodel
AT mmansor deeplearningapproachtowardsaccuratestateofchargeestimationforlithiumionbatteriesusingselfsupervisedtransformermodel
AT pinjernker deeplearningapproachtowardsaccuratestateofchargeestimationforlithiumionbatteriesusingselfsupervisedtransformermodel
AT zydong deeplearningapproachtowardsaccuratestateofchargeestimationforlithiumionbatteriesusingselfsupervisedtransformermodel
AT ksmsahari deeplearningapproachtowardsaccuratestateofchargeestimationforlithiumionbatteriesusingselfsupervisedtransformermodel
AT sktiong deeplearningapproachtowardsaccuratestateofchargeestimationforlithiumionbatteriesusingselfsupervisedtransformermodel
AT kmmuttaqi deeplearningapproachtowardsaccuratestateofchargeestimationforlithiumionbatteriesusingselfsupervisedtransformermodel
AT tmindramahlia deeplearningapproachtowardsaccuratestateofchargeestimationforlithiumionbatteriesusingselfsupervisedtransformermodel
AT fblaabjerg deeplearningapproachtowardsaccuratestateofchargeestimationforlithiumionbatteriesusingselfsupervisedtransformermodel
_version_ 1718381136741138432