Domain knowledge-guided machine learning framework for state of health estimation in Lithium-ion batteries

Abstract Accurate estimation of battery state of health is crucial for effective electric vehicle battery management. Here, we propose five health indicators that can be extracted online from real-world electric vehicle operation and develop a machine learning-based method to estimate the battery st...

Full description

Saved in:
Bibliographic Details
Main Authors: Andrea Lanubile, Pietro Bosoni, Gabriele Pozzato, Anirudh Allam, Matteo Acquarone, Simona Onori
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Communications Engineering
Online Access:https://doi.org/10.1038/s44172-024-00304-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846165179764572160
author Andrea Lanubile
Pietro Bosoni
Gabriele Pozzato
Anirudh Allam
Matteo Acquarone
Simona Onori
author_facet Andrea Lanubile
Pietro Bosoni
Gabriele Pozzato
Anirudh Allam
Matteo Acquarone
Simona Onori
author_sort Andrea Lanubile
collection DOAJ
description Abstract Accurate estimation of battery state of health is crucial for effective electric vehicle battery management. Here, we propose five health indicators that can be extracted online from real-world electric vehicle operation and develop a machine learning-based method to estimate the battery state of health. The proposed indicators provide physical insights into the energy and power fade of the battery and enable accurate capacity estimation even with partially missing data. Moreover, they can be computed for portions of the charging profile and real-world driving discharging conditions, facilitating real-time battery degradation estimation. The indicators are computed using experimental data from five cells aged under electric vehicle conditions, and a linear regression model is used to estimate the state of health. The results show that models trained with power autocorrelation and energy-based features achieve capacity estimation with maximum absolute percentage error within 1.5% to 2.5%.
format Article
id doaj-art-433453a6d3f34a3695136253a0bcef9e
institution Kabale University
issn 2731-3395
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Communications Engineering
spelling doaj-art-433453a6d3f34a3695136253a0bcef9e2024-11-17T12:30:59ZengNature PortfolioCommunications Engineering2731-33952024-11-013111310.1038/s44172-024-00304-2Domain knowledge-guided machine learning framework for state of health estimation in Lithium-ion batteriesAndrea Lanubile0Pietro Bosoni1Gabriele Pozzato2Anirudh Allam3Matteo Acquarone4Simona Onori5Energy Science & Engineering, Stanford UniversityEnergy Science & Engineering, Stanford UniversityEnergy Science & Engineering, Stanford UniversityEnergy Science & Engineering, Stanford UniversityEnergy Department, Politecnico di TorinoEnergy Science & Engineering, Stanford UniversityAbstract Accurate estimation of battery state of health is crucial for effective electric vehicle battery management. Here, we propose five health indicators that can be extracted online from real-world electric vehicle operation and develop a machine learning-based method to estimate the battery state of health. The proposed indicators provide physical insights into the energy and power fade of the battery and enable accurate capacity estimation even with partially missing data. Moreover, they can be computed for portions of the charging profile and real-world driving discharging conditions, facilitating real-time battery degradation estimation. The indicators are computed using experimental data from five cells aged under electric vehicle conditions, and a linear regression model is used to estimate the state of health. The results show that models trained with power autocorrelation and energy-based features achieve capacity estimation with maximum absolute percentage error within 1.5% to 2.5%.https://doi.org/10.1038/s44172-024-00304-2
spellingShingle Andrea Lanubile
Pietro Bosoni
Gabriele Pozzato
Anirudh Allam
Matteo Acquarone
Simona Onori
Domain knowledge-guided machine learning framework for state of health estimation in Lithium-ion batteries
Communications Engineering
title Domain knowledge-guided machine learning framework for state of health estimation in Lithium-ion batteries
title_full Domain knowledge-guided machine learning framework for state of health estimation in Lithium-ion batteries
title_fullStr Domain knowledge-guided machine learning framework for state of health estimation in Lithium-ion batteries
title_full_unstemmed Domain knowledge-guided machine learning framework for state of health estimation in Lithium-ion batteries
title_short Domain knowledge-guided machine learning framework for state of health estimation in Lithium-ion batteries
title_sort domain knowledge guided machine learning framework for state of health estimation in lithium ion batteries
url https://doi.org/10.1038/s44172-024-00304-2
work_keys_str_mv AT andrealanubile domainknowledgeguidedmachinelearningframeworkforstateofhealthestimationinlithiumionbatteries
AT pietrobosoni domainknowledgeguidedmachinelearningframeworkforstateofhealthestimationinlithiumionbatteries
AT gabrielepozzato domainknowledgeguidedmachinelearningframeworkforstateofhealthestimationinlithiumionbatteries
AT anirudhallam domainknowledgeguidedmachinelearningframeworkforstateofhealthestimationinlithiumionbatteries
AT matteoacquarone domainknowledgeguidedmachinelearningframeworkforstateofhealthestimationinlithiumionbatteries
AT simonaonori domainknowledgeguidedmachinelearningframeworkforstateofhealthestimationinlithiumionbatteries