Advanced Algorithm for SOC, Internal Resistance, and SOH Co-Estimation of Lithium-Titanate-Oxide Batteries Using Neural Networks

Lithium-titanate-oxide batteries can reduce the long charging time of electric vehicles by offering fast charging capabilities. However, high charging currents require an accurate estimation of battery internal state to prevent early aging of the battery and dangerous situations. An accurate algorit...

Full description

Saved in:
Bibliographic Details
Main Authors: Riccardo Di Dio, Roberto Di Rienzo, Gianluca Aurilio, Davide Cavaliere, Roberto Saletti
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Batteries
Subjects:
Online Access:https://www.mdpi.com/2313-0105/11/6/235
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849433435575156736
author Riccardo Di Dio
Roberto Di Rienzo
Gianluca Aurilio
Davide Cavaliere
Roberto Saletti
author_facet Riccardo Di Dio
Roberto Di Rienzo
Gianluca Aurilio
Davide Cavaliere
Roberto Saletti
author_sort Riccardo Di Dio
collection DOAJ
description Lithium-titanate-oxide batteries can reduce the long charging time of electric vehicles by offering fast charging capabilities. However, high charging currents require an accurate estimation of battery internal state to prevent early aging of the battery and dangerous situations. An accurate algorithm based on neural networks for the co-estimation of state of charge, internal resistance, and capacity state of health is proposed in this work. The algorithm is trained with synthetic data generated by an electric vehicle simulation platform running seven different standard driving cycles at various settings. The algorithm is then validated using an additional standard driving cycle, achieving, for state of charge, internal resistance, and capacity state of health, a root mean square error lower than 2%, 80 μΩ, and 2.9%, and a mean absolute percentage error lower than 3.4%, 4.4%, and 3.3%, respectively. The results obtained and the comparison with literature works indicate that the co-estimation algorithm proposed is able to estimate the considered quantities with very good accuracy.
format Article
id doaj-art-83d74bc1e2dc4a718c215b3f29ee5be1
institution Kabale University
issn 2313-0105
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Batteries
spelling doaj-art-83d74bc1e2dc4a718c215b3f29ee5be12025-08-20T03:27:02ZengMDPI AGBatteries2313-01052025-06-0111623510.3390/batteries11060235Advanced Algorithm for SOC, Internal Resistance, and SOH Co-Estimation of Lithium-Titanate-Oxide Batteries Using Neural NetworksRiccardo Di Dio0Roberto Di Rienzo1Gianluca Aurilio2Davide Cavaliere3Roberto Saletti4Marelli Europe S.p.A., Via del Timavo 33, 40131 Bologna, ItalyDipartimento di Ingegneria dell’Informazione, University of Pisa, Via Caruso 16, 56122 Pisa, ItalyMarelli Europe S.p.A., Via del Timavo 33, 40131 Bologna, ItalyMarelli Corporation, Kodama Plant, 540-7 Kyoei, Kodama-cho, Honjo-City 367-0206, Saitama, JapanDipartimento di Ingegneria dell’Informazione, University of Pisa, Via Caruso 16, 56122 Pisa, ItalyLithium-titanate-oxide batteries can reduce the long charging time of electric vehicles by offering fast charging capabilities. However, high charging currents require an accurate estimation of battery internal state to prevent early aging of the battery and dangerous situations. An accurate algorithm based on neural networks for the co-estimation of state of charge, internal resistance, and capacity state of health is proposed in this work. The algorithm is trained with synthetic data generated by an electric vehicle simulation platform running seven different standard driving cycles at various settings. The algorithm is then validated using an additional standard driving cycle, achieving, for state of charge, internal resistance, and capacity state of health, a root mean square error lower than 2%, 80 μΩ, and 2.9%, and a mean absolute percentage error lower than 3.4%, 4.4%, and 3.3%, respectively. The results obtained and the comparison with literature works indicate that the co-estimation algorithm proposed is able to estimate the considered quantities with very good accuracy.https://www.mdpi.com/2313-0105/11/6/235lithium titanate oxidebattery management systemco-estimation algorithmneural networksstate of chargeinternal resistance
spellingShingle Riccardo Di Dio
Roberto Di Rienzo
Gianluca Aurilio
Davide Cavaliere
Roberto Saletti
Advanced Algorithm for SOC, Internal Resistance, and SOH Co-Estimation of Lithium-Titanate-Oxide Batteries Using Neural Networks
Batteries
lithium titanate oxide
battery management system
co-estimation algorithm
neural networks
state of charge
internal resistance
title Advanced Algorithm for SOC, Internal Resistance, and SOH Co-Estimation of Lithium-Titanate-Oxide Batteries Using Neural Networks
title_full Advanced Algorithm for SOC, Internal Resistance, and SOH Co-Estimation of Lithium-Titanate-Oxide Batteries Using Neural Networks
title_fullStr Advanced Algorithm for SOC, Internal Resistance, and SOH Co-Estimation of Lithium-Titanate-Oxide Batteries Using Neural Networks
title_full_unstemmed Advanced Algorithm for SOC, Internal Resistance, and SOH Co-Estimation of Lithium-Titanate-Oxide Batteries Using Neural Networks
title_short Advanced Algorithm for SOC, Internal Resistance, and SOH Co-Estimation of Lithium-Titanate-Oxide Batteries Using Neural Networks
title_sort advanced algorithm for soc internal resistance and soh co estimation of lithium titanate oxide batteries using neural networks
topic lithium titanate oxide
battery management system
co-estimation algorithm
neural networks
state of charge
internal resistance
url https://www.mdpi.com/2313-0105/11/6/235
work_keys_str_mv AT riccardodidio advancedalgorithmforsocinternalresistanceandsohcoestimationoflithiumtitanateoxidebatteriesusingneuralnetworks
AT robertodirienzo advancedalgorithmforsocinternalresistanceandsohcoestimationoflithiumtitanateoxidebatteriesusingneuralnetworks
AT gianlucaaurilio advancedalgorithmforsocinternalresistanceandsohcoestimationoflithiumtitanateoxidebatteriesusingneuralnetworks
AT davidecavaliere advancedalgorithmforsocinternalresistanceandsohcoestimationoflithiumtitanateoxidebatteriesusingneuralnetworks
AT robertosaletti advancedalgorithmforsocinternalresistanceandsohcoestimationoflithiumtitanateoxidebatteriesusingneuralnetworks