Advancing battery state of charge estimation in electric vehicles through deep learning: A comprehensive study using real-world driving data

Accurately estimating the State of Charge (SOC) in Electric Vehicles (EVs) is critical for battery management and operational efficiency. This paper presents a Deep Learning (DL) approach to address this challenge, utilizing Feed-Forward Neural Networks (FFNN) to estimate SOC in real-world EV scenar...

Full description

Bibliographic Details
Main Authors: Mohd Herwan, Sulaiman, Zuriani, Mustaffa, Saifudin, Razali, Mohd Razali, Daud
Format: Article
Language:English
Published: Elsevier B.V. 2024
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/42347/
http://umpir.ump.edu.my/id/eprint/42347/1/Advancing%20battery%20state%20of%20charge%20estimation%20in%20electric%20vehicles.pdf
_version_ 1848826586526121984
author Mohd Herwan, Sulaiman
Zuriani, Mustaffa
Saifudin, Razali
Mohd Razali, Daud
author_facet Mohd Herwan, Sulaiman
Zuriani, Mustaffa
Saifudin, Razali
Mohd Razali, Daud
author_sort Mohd Herwan, Sulaiman
building UMP Institutional Repository
collection Online Access
description Accurately estimating the State of Charge (SOC) in Electric Vehicles (EVs) is critical for battery management and operational efficiency. This paper presents a Deep Learning (DL) approach to address this challenge, utilizing Feed-Forward Neural Networks (FFNN) to estimate SOC in real-world EV scenarios. The research used data from 70 driving sessions with a BMW i3 EV. Each session recorded key factors like voltage, current, and temperature, providing inputs for the DL model. The recorded SOC values served as outputs. We divided the dataset into training, validation, and testing subsets to develop and evaluate the FFNN model. The results demonstrate that the FFNN model yields minimal errors and significantly improves SOC estimation accuracy. Our comparative analysis with other machine learning techniques shows that FFNN outperforms them, with an approximately 2.87 % lower root mean square error (RMSE) compared to the second-best method, Extreme Learning Machine (ELM). This work has significant implications for electric vehicle battery management, demonstrating that deep learning methods can enhance SOC estimation, thereby improving the efficiency and reliability of EV operations.
first_indexed 2025-11-15T03:47:10Z
format Article
id ump-42347
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:47:10Z
publishDate 2024
publisher Elsevier B.V.
recordtype eprints
repository_type Digital Repository
spelling ump-423472024-08-14T03:45:45Z http://umpir.ump.edu.my/id/eprint/42347/ Advancing battery state of charge estimation in electric vehicles through deep learning: A comprehensive study using real-world driving data Mohd Herwan, Sulaiman Zuriani, Mustaffa Saifudin, Razali Mohd Razali, Daud TK Electrical engineering. Electronics Nuclear engineering Accurately estimating the State of Charge (SOC) in Electric Vehicles (EVs) is critical for battery management and operational efficiency. This paper presents a Deep Learning (DL) approach to address this challenge, utilizing Feed-Forward Neural Networks (FFNN) to estimate SOC in real-world EV scenarios. The research used data from 70 driving sessions with a BMW i3 EV. Each session recorded key factors like voltage, current, and temperature, providing inputs for the DL model. The recorded SOC values served as outputs. We divided the dataset into training, validation, and testing subsets to develop and evaluate the FFNN model. The results demonstrate that the FFNN model yields minimal errors and significantly improves SOC estimation accuracy. Our comparative analysis with other machine learning techniques shows that FFNN outperforms them, with an approximately 2.87 % lower root mean square error (RMSE) compared to the second-best method, Extreme Learning Machine (ELM). This work has significant implications for electric vehicle battery management, demonstrating that deep learning methods can enhance SOC estimation, thereby improving the efficiency and reliability of EV operations. Elsevier B.V. 2024-07-25 Article PeerReviewed pdf en cc_by_nc_4 http://umpir.ump.edu.my/id/eprint/42347/1/Advancing%20battery%20state%20of%20charge%20estimation%20in%20electric%20vehicles.pdf Mohd Herwan, Sulaiman and Zuriani, Mustaffa and Saifudin, Razali and Mohd Razali, Daud (2024) Advancing battery state of charge estimation in electric vehicles through deep learning: A comprehensive study using real-world driving data. Cleaner Energy Systems, 8 (100131). pp. 1-9. ISSN 2772-7831. (Published) https://doi.org/10.1016/j.cles.2024.100131 https://doi.org/10.1016/j.cles.2024.100131
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Mohd Herwan, Sulaiman
Zuriani, Mustaffa
Saifudin, Razali
Mohd Razali, Daud
Advancing battery state of charge estimation in electric vehicles through deep learning: A comprehensive study using real-world driving data
title Advancing battery state of charge estimation in electric vehicles through deep learning: A comprehensive study using real-world driving data
title_full Advancing battery state of charge estimation in electric vehicles through deep learning: A comprehensive study using real-world driving data
title_fullStr Advancing battery state of charge estimation in electric vehicles through deep learning: A comprehensive study using real-world driving data
title_full_unstemmed Advancing battery state of charge estimation in electric vehicles through deep learning: A comprehensive study using real-world driving data
title_short Advancing battery state of charge estimation in electric vehicles through deep learning: A comprehensive study using real-world driving data
title_sort advancing battery state of charge estimation in electric vehicles through deep learning: a comprehensive study using real-world driving data
topic TK Electrical engineering. Electronics Nuclear engineering
url http://umpir.ump.edu.my/id/eprint/42347/
http://umpir.ump.edu.my/id/eprint/42347/
http://umpir.ump.edu.my/id/eprint/42347/
http://umpir.ump.edu.my/id/eprint/42347/1/Advancing%20battery%20state%20of%20charge%20estimation%20in%20electric%20vehicles.pdf