Prediction of lithium-ion battery temperature in different operating conditions equipped with passive battery thermal management system by artificial neural networks

Lithium-ion batteries generate an enormous amount of heat during constant operation or rapid charge and discharge, which can result in a substantial increase in temperature, affecting the battery performance, reducing its cycle life, and potentially posing a safety issue. As a result, phase change m...

Full description

Bibliographic Details
Main Authors: Jaliliantabar, Farzad, Rizalman, Mamat, Sudhakar, Kumarasamy
Format: Article
Language:English
English
Published: Elsevier Ltd 2021
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/33843/
http://umpir.ump.edu.my/id/eprint/33843/1/Prediction%20of%20lithium-ion%20battery%20temperature%20in%20different%20operating_FULL.pdf
http://umpir.ump.edu.my/id/eprint/33843/2/Prediction%20of%20lithium-ion%20battery%20temperature%20in%20different%20operating.pdf
_version_ 1848824359353843712
author Jaliliantabar, Farzad
Rizalman, Mamat
Sudhakar, Kumarasamy
author_facet Jaliliantabar, Farzad
Rizalman, Mamat
Sudhakar, Kumarasamy
author_sort Jaliliantabar, Farzad
building UMP Institutional Repository
collection Online Access
description Lithium-ion batteries generate an enormous amount of heat during constant operation or rapid charge and discharge, which can result in a substantial increase in temperature, affecting the battery performance, reducing its cycle life, and potentially posing a safety issue. As a result, phase change materials (PCMs) based battery thermal management system (BTMS) can be used to control temperature of the battery and improve its performance. Moreover, with the increasing usage of artificial intelligence in a variety of disciplines, it appears to be worthwhile to investigate artificial intelligence approaches to evaluate various types of battery thermal management systems. The main aim of this study is to develop an artificial neural network (ANN) model for prediction of lithium-ion battery temperature equipped with a BTMS. The inputs of the model are discharge rate (1,2 ,3 and 4C), PCM thicknesses (0, 3, 6, 9, and 12 mm), Time (s) and PCM (with and without paraffin/ graphene PCM composite). The output of the model is temperature of the battery (C). Totally, 2012 data points were used to train, validation and test the model. The results of the study revealed capability of ANN to predict battery temperature in various operating conditions of BTMS. The R2, MSE, MAD and MAPE of the model were 0.99, 0.0173, 3.84 and 0.331, respectively. The results of the study have approved suitability of the ANN to predict performance of the passive BTMS.
first_indexed 2025-11-15T03:11:46Z
format Article
id ump-33843
institution Universiti Malaysia Pahang
institution_category Local University
language English
English
last_indexed 2025-11-15T03:11:46Z
publishDate 2021
publisher Elsevier Ltd
recordtype eprints
repository_type Digital Repository
spelling ump-338432022-06-22T01:34:21Z http://umpir.ump.edu.my/id/eprint/33843/ Prediction of lithium-ion battery temperature in different operating conditions equipped with passive battery thermal management system by artificial neural networks Jaliliantabar, Farzad Rizalman, Mamat Sudhakar, Kumarasamy TJ Mechanical engineering and machinery TL Motor vehicles. Aeronautics. Astronautics Lithium-ion batteries generate an enormous amount of heat during constant operation or rapid charge and discharge, which can result in a substantial increase in temperature, affecting the battery performance, reducing its cycle life, and potentially posing a safety issue. As a result, phase change materials (PCMs) based battery thermal management system (BTMS) can be used to control temperature of the battery and improve its performance. Moreover, with the increasing usage of artificial intelligence in a variety of disciplines, it appears to be worthwhile to investigate artificial intelligence approaches to evaluate various types of battery thermal management systems. The main aim of this study is to develop an artificial neural network (ANN) model for prediction of lithium-ion battery temperature equipped with a BTMS. The inputs of the model are discharge rate (1,2 ,3 and 4C), PCM thicknesses (0, 3, 6, 9, and 12 mm), Time (s) and PCM (with and without paraffin/ graphene PCM composite). The output of the model is temperature of the battery (C). Totally, 2012 data points were used to train, validation and test the model. The results of the study revealed capability of ANN to predict battery temperature in various operating conditions of BTMS. The R2, MSE, MAD and MAPE of the model were 0.99, 0.0173, 3.84 and 0.331, respectively. The results of the study have approved suitability of the ANN to predict performance of the passive BTMS. Elsevier Ltd 2021 Article PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/33843/1/Prediction%20of%20lithium-ion%20battery%20temperature%20in%20different%20operating_FULL.pdf pdf en http://umpir.ump.edu.my/id/eprint/33843/2/Prediction%20of%20lithium-ion%20battery%20temperature%20in%20different%20operating.pdf Jaliliantabar, Farzad and Rizalman, Mamat and Sudhakar, Kumarasamy (2021) Prediction of lithium-ion battery temperature in different operating conditions equipped with passive battery thermal management system by artificial neural networks. Materials Today: Proceedings, 48 (6). pp. 1796-1804. ISSN 2214-7853. (Published) https://doi.org/10.1016/j.matpr.2021.09.026 https://doi.org/10.1016/j.matpr.2021.09.026
spellingShingle TJ Mechanical engineering and machinery
TL Motor vehicles. Aeronautics. Astronautics
Jaliliantabar, Farzad
Rizalman, Mamat
Sudhakar, Kumarasamy
Prediction of lithium-ion battery temperature in different operating conditions equipped with passive battery thermal management system by artificial neural networks
title Prediction of lithium-ion battery temperature in different operating conditions equipped with passive battery thermal management system by artificial neural networks
title_full Prediction of lithium-ion battery temperature in different operating conditions equipped with passive battery thermal management system by artificial neural networks
title_fullStr Prediction of lithium-ion battery temperature in different operating conditions equipped with passive battery thermal management system by artificial neural networks
title_full_unstemmed Prediction of lithium-ion battery temperature in different operating conditions equipped with passive battery thermal management system by artificial neural networks
title_short Prediction of lithium-ion battery temperature in different operating conditions equipped with passive battery thermal management system by artificial neural networks
title_sort prediction of lithium-ion battery temperature in different operating conditions equipped with passive battery thermal management system by artificial neural networks
topic TJ Mechanical engineering and machinery
TL Motor vehicles. Aeronautics. Astronautics
url http://umpir.ump.edu.my/id/eprint/33843/
http://umpir.ump.edu.my/id/eprint/33843/
http://umpir.ump.edu.my/id/eprint/33843/
http://umpir.ump.edu.my/id/eprint/33843/1/Prediction%20of%20lithium-ion%20battery%20temperature%20in%20different%20operating_FULL.pdf
http://umpir.ump.edu.my/id/eprint/33843/2/Prediction%20of%20lithium-ion%20battery%20temperature%20in%20different%20operating.pdf