Particle swarm optimized back propagation neural network for state of health estimation of lithium-ion battery

The assessment and monitoring of battery health is very crucial for the maintenance and safety of battery-powered applications such as Electric vehicles (EVs). To conduct appropriate battery operation in EVs, the battery capacity should be estimated accurately. In this regard, the State of health...

Full description

Bibliographic Details
Main Authors: Afida Ayob, Shaheer Ansari, Aini Hussain, Mohamad Hanif Md Saad, M. S. Hossain Lipu
Format: Article
Language:English
Published: Penerbit Universiti Kebangsaan Malaysia 2024
Online Access:http://journalarticle.ukm.my/25154/
http://journalarticle.ukm.my/25154/1/34.pdf
_version_ 1848816283391361024
author Afida Ayob,
Shaheer Ansari,
Aini Hussain,
Mohamad Hanif Md Saad,
M. S. Hossain Lipu,
author_facet Afida Ayob,
Shaheer Ansari,
Aini Hussain,
Mohamad Hanif Md Saad,
M. S. Hossain Lipu,
author_sort Afida Ayob,
building UKM Institutional Repository
collection Online Access
description The assessment and monitoring of battery health is very crucial for the maintenance and safety of battery-powered applications such as Electric vehicles (EVs). To conduct appropriate battery operation in EVs, the battery capacity should be estimated accurately. In this regard, the State of health (SOH) estimation is conducted for evaluating the battery aging status. This work proposes a hybrid backpropagation neural network (BPNN) and particle swarm optimization (PSO) technique for SOH estimation. A multi-feature input data framework is constructed with 31-dimensional features for the model training by using 4 battery datasets from NASA i.e. B5, B6, B7 and B18. The acquisition of the data samples has been performed with a systematic sampling technique. The presented work is conducted with a training testing ratio of 70:30 and validated with the MIT Stanford battery dataset. The experimental outcomes demonstrated high SOH estimation accuracy compared with the conventional BPNN model. In the case of battery B5, it was observed that RMSE, MSE and MAPE for the BPNN-PSO model are 0.6791, 0.0046, 0.3203 compared with the conventional BPNN model i.e. 0.8796, 0.0077, 0.4881 respectively. Furthermore, the significance of capacity regeneration in B7 and B18 results in high-performance metrics compared with other battery datasets. The research conducted would be beneficial to estimate the battery status regarding battery health i.e. SOH accurately in Battery System Management (BMS) based EV application.
first_indexed 2025-11-15T01:03:25Z
format Article
id oai:generic.eprints.org:25154
institution Universiti Kebangasaan Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T01:03:25Z
publishDate 2024
publisher Penerbit Universiti Kebangsaan Malaysia
recordtype eprints
repository_type Digital Repository
spelling oai:generic.eprints.org:251542025-05-26T09:00:03Z http://journalarticle.ukm.my/25154/ Particle swarm optimized back propagation neural network for state of health estimation of lithium-ion battery Afida Ayob, Shaheer Ansari, Aini Hussain, Mohamad Hanif Md Saad, M. S. Hossain Lipu, The assessment and monitoring of battery health is very crucial for the maintenance and safety of battery-powered applications such as Electric vehicles (EVs). To conduct appropriate battery operation in EVs, the battery capacity should be estimated accurately. In this regard, the State of health (SOH) estimation is conducted for evaluating the battery aging status. This work proposes a hybrid backpropagation neural network (BPNN) and particle swarm optimization (PSO) technique for SOH estimation. A multi-feature input data framework is constructed with 31-dimensional features for the model training by using 4 battery datasets from NASA i.e. B5, B6, B7 and B18. The acquisition of the data samples has been performed with a systematic sampling technique. The presented work is conducted with a training testing ratio of 70:30 and validated with the MIT Stanford battery dataset. The experimental outcomes demonstrated high SOH estimation accuracy compared with the conventional BPNN model. In the case of battery B5, it was observed that RMSE, MSE and MAPE for the BPNN-PSO model are 0.6791, 0.0046, 0.3203 compared with the conventional BPNN model i.e. 0.8796, 0.0077, 0.4881 respectively. Furthermore, the significance of capacity regeneration in B7 and B18 results in high-performance metrics compared with other battery datasets. The research conducted would be beneficial to estimate the battery status regarding battery health i.e. SOH accurately in Battery System Management (BMS) based EV application. Penerbit Universiti Kebangsaan Malaysia 2024 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/25154/1/34.pdf Afida Ayob, and Shaheer Ansari, and Aini Hussain, and Mohamad Hanif Md Saad, and M. S. Hossain Lipu, (2024) Particle swarm optimized back propagation neural network for state of health estimation of lithium-ion battery. Jurnal Kejuruteraan, 36 (1). pp. 365-373. ISSN 0128-0198 https://www.ukm.my/jkukm/volume-3601-2024
spellingShingle Afida Ayob,
Shaheer Ansari,
Aini Hussain,
Mohamad Hanif Md Saad,
M. S. Hossain Lipu,
Particle swarm optimized back propagation neural network for state of health estimation of lithium-ion battery
title Particle swarm optimized back propagation neural network for state of health estimation of lithium-ion battery
title_full Particle swarm optimized back propagation neural network for state of health estimation of lithium-ion battery
title_fullStr Particle swarm optimized back propagation neural network for state of health estimation of lithium-ion battery
title_full_unstemmed Particle swarm optimized back propagation neural network for state of health estimation of lithium-ion battery
title_short Particle swarm optimized back propagation neural network for state of health estimation of lithium-ion battery
title_sort particle swarm optimized back propagation neural network for state of health estimation of lithium-ion battery
url http://journalarticle.ukm.my/25154/
http://journalarticle.ukm.my/25154/
http://journalarticle.ukm.my/25154/1/34.pdf