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...
Saved in:
| Main Authors: | , , , , |
|---|---|
| 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 |