General Machine Learning Approaches for Lithium-Ion Battery Capacity Fade Compared to Empirical Models

Today’s growing demand for lithium-ion batteries across various industrial sectors has introduced a new concern: battery aging. This issue necessitates the development of tools and models that can accurately predict battery aging. This study proposes a general framework for constructing battery agin...

Full description

Saved in:
Bibliographic Details
Main Authors: Quentin Mayemba, Gabriel Ducret, An Li, Rémy Mingant, Pascal Venet
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Batteries
Subjects:
Online Access:https://www.mdpi.com/2313-0105/10/10/367
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204792123555840
author Quentin Mayemba
Gabriel Ducret
An Li
Rémy Mingant
Pascal Venet
author_facet Quentin Mayemba
Gabriel Ducret
An Li
Rémy Mingant
Pascal Venet
author_sort Quentin Mayemba
collection DOAJ
description Today’s growing demand for lithium-ion batteries across various industrial sectors has introduced a new concern: battery aging. This issue necessitates the development of tools and models that can accurately predict battery aging. This study proposes a general framework for constructing battery aging models using machine learning techniques and compares these models with two existing empirical models, including a commercial one. To build the models, the databases produced by EVERLASTING and Bills et al. were utilized. The aim is to create universally applicable models that can address any battery-aging scenario. In this study, three types of models were developed: a vanilla neural network, a neural network inspired by extreme learning machines, and an encoder coupled with a neural network. The inputs for these models are derived from established knowledge in battery science, allowing the models to capture aging effects across different use cases. The models were trained on cells subjected to specific aging conditions and they were tested on other cells from the same database that experienced different aging conditions. The results obtained during the test for the vanilla neural network showed an RMSE of 1.3% on the Bills et al. test data and an RMSE of 2.7% on the EVERLASTING data, demonstrating similar or superior performance compared to the empirical models and proving the ability of the models to capture battery aging.
format Article
id doaj-art-6093c301b29f4e12a3ffcb2e0ba7c317
institution OA Journals
issn 2313-0105
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Batteries
spelling doaj-art-6093c301b29f4e12a3ffcb2e0ba7c3172025-08-20T02:11:14ZengMDPI AGBatteries2313-01052024-10-01101036710.3390/batteries10100367General Machine Learning Approaches for Lithium-Ion Battery Capacity Fade Compared to Empirical ModelsQuentin Mayemba0Gabriel Ducret1An Li2Rémy Mingant3Pascal Venet4Siemens Digital Industries Software, 19 Boulevard Jules Carteret, 69007 Lyon, FranceIFP Energies Nouvelles, 1-4 Avenue du Bois Préau, 92500 Rueil-Malmaison, FranceSiemens Digital Industries Software, 19 Boulevard Jules Carteret, 69007 Lyon, FranceIFP Energies Nouvelles, Rond-Point de L’échangeur de Solaize, 69360 Solaize, FranceUniversité Claude Bernard Lyon 1, Ampère, UMR5005, INSA Lyon, Ecole Centrale de Lyon, CNRS, F-69100 Villeurbanne, FranceToday’s growing demand for lithium-ion batteries across various industrial sectors has introduced a new concern: battery aging. This issue necessitates the development of tools and models that can accurately predict battery aging. This study proposes a general framework for constructing battery aging models using machine learning techniques and compares these models with two existing empirical models, including a commercial one. To build the models, the databases produced by EVERLASTING and Bills et al. were utilized. The aim is to create universally applicable models that can address any battery-aging scenario. In this study, three types of models were developed: a vanilla neural network, a neural network inspired by extreme learning machines, and an encoder coupled with a neural network. The inputs for these models are derived from established knowledge in battery science, allowing the models to capture aging effects across different use cases. The models were trained on cells subjected to specific aging conditions and they were tested on other cells from the same database that experienced different aging conditions. The results obtained during the test for the vanilla neural network showed an RMSE of 1.3% on the Bills et al. test data and an RMSE of 2.7% on the EVERLASTING data, demonstrating similar or superior performance compared to the empirical models and proving the ability of the models to capture battery aging.https://www.mdpi.com/2313-0105/10/10/367capacity lossbattery agingempirical modelmachine learningartificial neural networkautoencoder
spellingShingle Quentin Mayemba
Gabriel Ducret
An Li
Rémy Mingant
Pascal Venet
General Machine Learning Approaches for Lithium-Ion Battery Capacity Fade Compared to Empirical Models
Batteries
capacity loss
battery aging
empirical model
machine learning
artificial neural network
autoencoder
title General Machine Learning Approaches for Lithium-Ion Battery Capacity Fade Compared to Empirical Models
title_full General Machine Learning Approaches for Lithium-Ion Battery Capacity Fade Compared to Empirical Models
title_fullStr General Machine Learning Approaches for Lithium-Ion Battery Capacity Fade Compared to Empirical Models
title_full_unstemmed General Machine Learning Approaches for Lithium-Ion Battery Capacity Fade Compared to Empirical Models
title_short General Machine Learning Approaches for Lithium-Ion Battery Capacity Fade Compared to Empirical Models
title_sort general machine learning approaches for lithium ion battery capacity fade compared to empirical models
topic capacity loss
battery aging
empirical model
machine learning
artificial neural network
autoencoder
url https://www.mdpi.com/2313-0105/10/10/367
work_keys_str_mv AT quentinmayemba generalmachinelearningapproachesforlithiumionbatterycapacityfadecomparedtoempiricalmodels
AT gabrielducret generalmachinelearningapproachesforlithiumionbatterycapacityfadecomparedtoempiricalmodels
AT anli generalmachinelearningapproachesforlithiumionbatterycapacityfadecomparedtoempiricalmodels
AT remymingant generalmachinelearningapproachesforlithiumionbatterycapacityfadecomparedtoempiricalmodels
AT pascalvenet generalmachinelearningapproachesforlithiumionbatterycapacityfadecomparedtoempiricalmodels