Publication:
State-of-Charge Estimation of Li-ion Battery Using Gated Recurrent Unit with One-Cycle Learning Rate Policy

Simple item page
dc.citedby17
dc.contributor.authorHannan M.A.en_US
dc.contributor.authorHow D.N.T.en_US
dc.contributor.authorMansor M.B.en_US
dc.contributor.authorHossain Lipu M.S.en_US
dc.contributor.authorKer P.en_US
dc.contributor.authorMuttaqi K.en_US
dc.contributor.authorid7103014445en_US
dc.contributor.authorid57212923888en_US
dc.contributor.authorid6701749037en_US
dc.contributor.authorid36518949700en_US
dc.contributor.authorid37461740800en_US
dc.contributor.authorid55582332500en_US
dc.date.accessioned2023-05-29T09:08:01Z
dc.date.available2023-05-29T09:08:01Z
dc.date.issued2021
dc.descriptionCharging (batteries); Deep learning; Digital arithmetic; Electric traction; Ions; Learning systems; Lithium compounds; Lithium-ion batteries; Statistical tests; Comparative evaluations; Feed-forward architectures; Floating point operations per seconds; Generalization capability; Lightweight batteries; Model computation; State-of-charge estimation; Vehicle applications; Battery management systemsen_US
dc.description.abstractDeep learning has gained much traction in application to state-of-charge (SOC) estimation for Li-ion batteries in electric vehicle applications. However, with the vast selection of architectures and hyperparameter combinations, it remains challenging to design an accurate and robust SOC estimation model with a sufficiently low computation cost. Therefore, this study provides a comparative evaluation among commonly used deep learning models from the recurrent, convolutional, and feedforward architecture benchmarked on an openly available Li-ion battery dataset. To evaluate model robustness and generalization capability, we train and test models on different drive cycles at various temperatures and compute the root mean squared error (RMSE) and mean absolute error metric. To evaluate model computation costs, we run models in real-time and record the model size, floating-point operations per second (FLOPS), and run-time duration per datapoint. This study proposes a two-hidden layer stacked gated recurrent unit model trained with a one-cycle policy learning rate scheduler. The proposed model achieves a minimum RMSE of 0.52% on the train dataset and 0.65% on the test dataset while maintaining a relatively low computation cost. Executing the proposed model in real-time takes up approximately 1 MB in disk space, 300K FLOPS, and 0.03 ms run-time per datapoint. This makes the proposed model feasible to be executed on lightweight battery management system processors. � 1972-2012 IEEE.en_US
dc.description.natureFinalen_US
dc.identifier.ArtNo9376269
dc.identifier.doi10.1109/TIA.2021.3065194
dc.identifier.epage2971
dc.identifier.issue3
dc.identifier.scopus2-s2.0-85102685878
dc.identifier.spage2964
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85102685878&doi=10.1109%2fTIA.2021.3065194&partnerID=40&md5=e4ee8c69f2cf6b14cd0cd536bdc38879
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/26228
dc.identifier.volume57
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.sourceScopus
dc.sourcetitleIEEE Transactions on Industry Applications
dc.titleState-of-Charge Estimation of Li-ion Battery Using Gated Recurrent Unit with One-Cycle Learning Rate Policyen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS