Cover Image

Using the evolutionary mating algorithm for optimizing deep learning parameters for battery state of charge estimation of electric vehicle

This paper presents the application of a recent metaheuristic algorithm namely Evolutionary Mating Algorithm (EMA) for optimizing the Deep Learning (DL) parameters to estimate the state of charge (SOC) of a battery for an electric vehicle in the real environment. The recorded data were obtained from...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohd Herwan, Sulaiman, Zuriani, Mustaffa, Nor Farizan, Zakaria, Mohd Mawardi, Saari
Format: Article
Language:English
English
Published: Elsevier 2023
Subjects:
QA75 Electronic computers. Computer science
TK Electrical engineering. Electronics Nuclear engineering
Online Access:http://umpir.ump.edu.my/id/eprint/39044/1/Using%20the%20evolutionary%20mating%20algorithm%20for%20optimizing%20deep%20learning%20parameters.pdf
http://umpir.ump.edu.my/id/eprint/39044/2/Using%20the%20evolutionary%20mating%20algorithm%20for%20optimizing%20deep%20learning%20parameters%20for%20battery%20state%20of%20charge%20estimation%20of%20electric%20vehicle.pdf
http://umpir.ump.edu.my/id/eprint/39044/
https://doi.org/10.1016/j.energy.2023.128094
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.ump.umpir.39044
record_format eprints
spelling my.ump.umpir.390442023-10-26T04:32:12Z http://umpir.ump.edu.my/id/eprint/39044/ Using the evolutionary mating algorithm for optimizing deep learning parameters for battery state of charge estimation of electric vehicle Mohd Herwan, Sulaiman Zuriani, Mustaffa Nor Farizan, Zakaria Mohd Mawardi, Saari QA75 Electronic computers. Computer science TK Electrical engineering. Electronics Nuclear engineering This paper presents the application of a recent metaheuristic algorithm namely Evolutionary Mating Algorithm (EMA) for optimizing the Deep Learning (DL) parameters to estimate the state of charge (SOC) of a battery for an electric vehicle in the real environment. The recorded data were obtained from 70 real driving trips of a BMW i3 EV, where the inputs of the DL were the voltage, current, battery temperature and ambient temperature while the output was the real SOC recorded during all trips. The data were divided into 60 trips for training and the final 10 trips for testing the performance of the developed EMA-DL model. The findings of the study demonstrated the promising results of EMA-DL in terms of obtaining the minimum error, which significantly increases the accuracy of the SOC estimation. To show the effectiveness of EMA-DL, comparison studies were conducted among other metaheuristic optimizers that were also used to optimize the DL parameters viz, Particles Swarm Optimization (PSO), Genetic Algorithm (GA), Differential Evolution (DE) as well as the Adaptive Moment Estimation (ADAM). According to the simulation results, the proposed EMA-DL algorithm was found to outperform all the other compared algorithms based on the evaluated metrics. Thus, it can be employed as a proficient technique to accurately estimate the state of charge (SOC) of electric vehicle batteries. Elsevier 2023-06 Article PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/39044/1/Using%20the%20evolutionary%20mating%20algorithm%20for%20optimizing%20deep%20learning%20parameters.pdf pdf en http://umpir.ump.edu.my/id/eprint/39044/2/Using%20the%20evolutionary%20mating%20algorithm%20for%20optimizing%20deep%20learning%20parameters%20for%20battery%20state%20of%20charge%20estimation%20of%20electric%20vehicle.pdf Mohd Herwan, Sulaiman and Zuriani, Mustaffa and Nor Farizan, Zakaria and Mohd Mawardi, Saari (2023) Using the evolutionary mating algorithm for optimizing deep learning parameters for battery state of charge estimation of electric vehicle. Energy, 279 (128094). ISSN 0360-5442 (Print), 1873-6785 (Online). (Published) https://doi.org/10.1016/j.energy.2023.128094 10.1016/j.energy.2023.128094
institution Universiti Malaysia Pahang Al-Sultan Abdullah
building UMPSA Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Pahang Al-Sultan Abdullah
content_source UMPSA Institutional Repository
url_provider http://umpir.ump.edu.my/
language English
English
topic QA75 Electronic computers. Computer science
TK Electrical engineering. Electronics Nuclear engineering
spellingShingle QA75 Electronic computers. Computer science
TK Electrical engineering. Electronics Nuclear engineering
Mohd Herwan, Sulaiman
Zuriani, Mustaffa
Nor Farizan, Zakaria
Mohd Mawardi, Saari
Using the evolutionary mating algorithm for optimizing deep learning parameters for battery state of charge estimation of electric vehicle
description This paper presents the application of a recent metaheuristic algorithm namely Evolutionary Mating Algorithm (EMA) for optimizing the Deep Learning (DL) parameters to estimate the state of charge (SOC) of a battery for an electric vehicle in the real environment. The recorded data were obtained from 70 real driving trips of a BMW i3 EV, where the inputs of the DL were the voltage, current, battery temperature and ambient temperature while the output was the real SOC recorded during all trips. The data were divided into 60 trips for training and the final 10 trips for testing the performance of the developed EMA-DL model. The findings of the study demonstrated the promising results of EMA-DL in terms of obtaining the minimum error, which significantly increases the accuracy of the SOC estimation. To show the effectiveness of EMA-DL, comparison studies were conducted among other metaheuristic optimizers that were also used to optimize the DL parameters viz, Particles Swarm Optimization (PSO), Genetic Algorithm (GA), Differential Evolution (DE) as well as the Adaptive Moment Estimation (ADAM). According to the simulation results, the proposed EMA-DL algorithm was found to outperform all the other compared algorithms based on the evaluated metrics. Thus, it can be employed as a proficient technique to accurately estimate the state of charge (SOC) of electric vehicle batteries.
format Article
author Mohd Herwan, Sulaiman
Zuriani, Mustaffa
Nor Farizan, Zakaria
Mohd Mawardi, Saari
author_facet Mohd Herwan, Sulaiman
Zuriani, Mustaffa
Nor Farizan, Zakaria
Mohd Mawardi, Saari
author_sort Mohd Herwan, Sulaiman
title Using the evolutionary mating algorithm for optimizing deep learning parameters for battery state of charge estimation of electric vehicle
title_short Using the evolutionary mating algorithm for optimizing deep learning parameters for battery state of charge estimation of electric vehicle
title_full Using the evolutionary mating algorithm for optimizing deep learning parameters for battery state of charge estimation of electric vehicle
title_fullStr Using the evolutionary mating algorithm for optimizing deep learning parameters for battery state of charge estimation of electric vehicle
title_full_unstemmed Using the evolutionary mating algorithm for optimizing deep learning parameters for battery state of charge estimation of electric vehicle
title_sort using the evolutionary mating algorithm for optimizing deep learning parameters for battery state of charge estimation of electric vehicle
publisher Elsevier
publishDate 2023
url http://umpir.ump.edu.my/id/eprint/39044/1/Using%20the%20evolutionary%20mating%20algorithm%20for%20optimizing%20deep%20learning%20parameters.pdf
http://umpir.ump.edu.my/id/eprint/39044/2/Using%20the%20evolutionary%20mating%20algorithm%20for%20optimizing%20deep%20learning%20parameters%20for%20battery%20state%20of%20charge%20estimation%20of%20electric%20vehicle.pdf
http://umpir.ump.edu.my/id/eprint/39044/
https://doi.org/10.1016/j.energy.2023.128094
_version_ 1822923815410204672
score 13.232414

Similar Items