Machine learning for battery quality classification and lifetime prediction using formation data

Accurate classification of battery quality and prediction of battery lifetime before leaving the factory would bring economic and safety benefits. Here, we propose a data-driven approach with machine learning to classify the battery quality and predict the battery lifetime before usage only using fo...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiayu Zou, Yingbo Gao, Moritz H. Frieges, Martin F. Börner, Achim Kampker, Weihan Li
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Energy and AI
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666546824001174
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846117675630067712
author Jiayu Zou
Yingbo Gao
Moritz H. Frieges
Martin F. Börner
Achim Kampker
Weihan Li
author_facet Jiayu Zou
Yingbo Gao
Moritz H. Frieges
Martin F. Börner
Achim Kampker
Weihan Li
author_sort Jiayu Zou
collection DOAJ
description Accurate classification of battery quality and prediction of battery lifetime before leaving the factory would bring economic and safety benefits. Here, we propose a data-driven approach with machine learning to classify the battery quality and predict the battery lifetime before usage only using formation data. We extract three classes of features from the raw formation data, considering the statistical aspects, differential analysis, and electrochemical characteristics. The correlation between over 100 extracted features and the battery lifetime is analysed based on the ageing mechanisms. Machine learning models are developed to classify battery quality and predict battery lifetime by features with a high correlation with battery ageing. The validation results show that the quality classification model achieved accuracies of 89.74% and 89.47% for the batteries aged at 25°C and 45°C, respectively. Moreover, the lifetime prediction model is able to predict the battery end-of-life with mean percentage errors of 6.50% and 5.45% for the batteries aged at 25°C and 45°C, respectively. This work highlights the potential of battery formation data from production lines in quality classification and lifetime prediction.
format Article
id doaj-art-ee70a1a2032b4f708af2f82f3a6e0489
institution Kabale University
issn 2666-5468
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Energy and AI
spelling doaj-art-ee70a1a2032b4f708af2f82f3a6e04892024-12-18T08:53:08ZengElsevierEnergy and AI2666-54682024-12-0118100451Machine learning for battery quality classification and lifetime prediction using formation dataJiayu Zou0Yingbo Gao1Moritz H. Frieges2Martin F. Börner3Achim Kampker4Weihan Li5Chair for Electrochemical Energy Conversion and Storage Systems, Institute for Power Electronics and Electrical Drives (ISEA), RWTH Aachen University, Campus-Boulevard 89, 52074 Aachen, Germany; Center for Ageing, Reliability and Lifetime Prediction of Electrochemical and Power Electronic Systems (CARL), RWTH Aachen University, Campus-Boulevard 89, Aachen, Germany; Juelich Aachen Research Alliance, JARA-Energy, GermanyDepartment of Computer Science, RWTH Aachen University, 52056 Aachen, GermanyChair of Production Engineering of E-Mobility Components (PEM), RWTH Aachen University, Bohr 12, 52072 Aachen, GermanyChair for Electrochemical Energy Conversion and Storage Systems, Institute for Power Electronics and Electrical Drives (ISEA), RWTH Aachen University, Campus-Boulevard 89, 52074 Aachen, Germany; Center for Ageing, Reliability and Lifetime Prediction of Electrochemical and Power Electronic Systems (CARL), RWTH Aachen University, Campus-Boulevard 89, Aachen, Germany; Juelich Aachen Research Alliance, JARA-Energy, GermanyChair of Production Engineering of E-Mobility Components (PEM), RWTH Aachen University, Bohr 12, 52072 Aachen, GermanyChair for Electrochemical Energy Conversion and Storage Systems, Institute for Power Electronics and Electrical Drives (ISEA), RWTH Aachen University, Campus-Boulevard 89, 52074 Aachen, Germany; Center for Ageing, Reliability and Lifetime Prediction of Electrochemical and Power Electronic Systems (CARL), RWTH Aachen University, Campus-Boulevard 89, Aachen, Germany; Juelich Aachen Research Alliance, JARA-Energy, Germany; Corresponding author.Accurate classification of battery quality and prediction of battery lifetime before leaving the factory would bring economic and safety benefits. Here, we propose a data-driven approach with machine learning to classify the battery quality and predict the battery lifetime before usage only using formation data. We extract three classes of features from the raw formation data, considering the statistical aspects, differential analysis, and electrochemical characteristics. The correlation between over 100 extracted features and the battery lifetime is analysed based on the ageing mechanisms. Machine learning models are developed to classify battery quality and predict battery lifetime by features with a high correlation with battery ageing. The validation results show that the quality classification model achieved accuracies of 89.74% and 89.47% for the batteries aged at 25°C and 45°C, respectively. Moreover, the lifetime prediction model is able to predict the battery end-of-life with mean percentage errors of 6.50% and 5.45% for the batteries aged at 25°C and 45°C, respectively. This work highlights the potential of battery formation data from production lines in quality classification and lifetime prediction.http://www.sciencedirect.com/science/article/pii/S2666546824001174BatteryFormationQuality classificationLife predictionMachine learning
spellingShingle Jiayu Zou
Yingbo Gao
Moritz H. Frieges
Martin F. Börner
Achim Kampker
Weihan Li
Machine learning for battery quality classification and lifetime prediction using formation data
Energy and AI
Battery
Formation
Quality classification
Life prediction
Machine learning
title Machine learning for battery quality classification and lifetime prediction using formation data
title_full Machine learning for battery quality classification and lifetime prediction using formation data
title_fullStr Machine learning for battery quality classification and lifetime prediction using formation data
title_full_unstemmed Machine learning for battery quality classification and lifetime prediction using formation data
title_short Machine learning for battery quality classification and lifetime prediction using formation data
title_sort machine learning for battery quality classification and lifetime prediction using formation data
topic Battery
Formation
Quality classification
Life prediction
Machine learning
url http://www.sciencedirect.com/science/article/pii/S2666546824001174
work_keys_str_mv AT jiayuzou machinelearningforbatteryqualityclassificationandlifetimepredictionusingformationdata
AT yingbogao machinelearningforbatteryqualityclassificationandlifetimepredictionusingformationdata
AT moritzhfrieges machinelearningforbatteryqualityclassificationandlifetimepredictionusingformationdata
AT martinfborner machinelearningforbatteryqualityclassificationandlifetimepredictionusingformationdata
AT achimkampker machinelearningforbatteryqualityclassificationandlifetimepredictionusingformationdata
AT weihanli machinelearningforbatteryqualityclassificationandlifetimepredictionusingformationdata