Improved SOH Prediction of Lithium-Ion Batteries Based on Multi-Dimensional Feature Analysis and Transformer Framework

Data-driven state-of-health (SOH) prediction is increasingly critical for the effective management of lithium-ion batteries; however, challenges remain in practical applications. Traditional methods that rely on a single health indicator often fail to capture the complexity and multi-dimensional nat...

Full description

Saved in:
Bibliographic Details
Main Authors: Tianfeng Long, Pengcheng Zhang, Xiaoqi Liu, Huaqing Shang, Meiling Yue, Xuesong Shen, Jianwen Meng
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of Vehicular Technology
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11015565/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850161460037025792
author Tianfeng Long
Pengcheng Zhang
Xiaoqi Liu
Huaqing Shang
Meiling Yue
Xuesong Shen
Jianwen Meng
author_facet Tianfeng Long
Pengcheng Zhang
Xiaoqi Liu
Huaqing Shang
Meiling Yue
Xuesong Shen
Jianwen Meng
author_sort Tianfeng Long
collection DOAJ
description Data-driven state-of-health (SOH) prediction is increasingly critical for the effective management of lithium-ion batteries; however, challenges remain in practical applications. Traditional methods that rely on a single health indicator often fail to capture the complexity and multi-dimensional nature of battery performance changes. To address these limitations, this paper presents a novel Transformer-based approach for accurate SOH prediction. The correlation between various measured and computed features extracted from battery charge/discharge curves and their impact on battery performance degradation are investigated using Pearson correlation coefficients. Three strongly correlated features are identified as multiple input variables for the Transformer framework. The effectiveness of this Transformer-based SOH prediction method is demonstrated using public datasets, revealing that predictions for internal resistance and capacity closely align with actual values, with most RMSE values falling below 0.01. Furthermore, validation with an additional laboratory dataset confirms the accuracy and adaptability of our proposed approach, highlighting its potential to enhance SOH prediction in real-world applications.
format Article
id doaj-art-a1014411084a45f08cfc5edba7e39318
institution OA Journals
issn 2644-1330
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of Vehicular Technology
spelling doaj-art-a1014411084a45f08cfc5edba7e393182025-08-20T02:22:49ZengIEEEIEEE Open Journal of Vehicular Technology2644-13302025-01-0161363137910.1109/OJVT.2025.357370511015565Improved SOH Prediction of Lithium-Ion Batteries Based on Multi-Dimensional Feature Analysis and Transformer FrameworkTianfeng Long0https://orcid.org/0009-0002-6297-8963Pengcheng Zhang1https://orcid.org/0009-0006-0314-452XXiaoqi Liu2https://orcid.org/0009-0003-9810-0279Huaqing Shang3Meiling Yue4https://orcid.org/0000-0002-4624-4743Xuesong Shen5Jianwen Meng6https://orcid.org/0000-0001-5539-464XSchool of Mechnical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, ChinaSchool of Mechnical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, ChinaSchool of Mechnical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, ChinaSchool of Mechnical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, ChinaSchool of Mechnical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, ChinaNational Center of Technology Innovation for Fuel Cell, Shandong Guochuang Fuel Cell Technology Innovation Center Company Ltd., Weifang, ChinaEcole Supérieure des Techniques Aéronautiques et de Construction Automobile, Montigny-le-Bretonneux, FranceData-driven state-of-health (SOH) prediction is increasingly critical for the effective management of lithium-ion batteries; however, challenges remain in practical applications. Traditional methods that rely on a single health indicator often fail to capture the complexity and multi-dimensional nature of battery performance changes. To address these limitations, this paper presents a novel Transformer-based approach for accurate SOH prediction. The correlation between various measured and computed features extracted from battery charge/discharge curves and their impact on battery performance degradation are investigated using Pearson correlation coefficients. Three strongly correlated features are identified as multiple input variables for the Transformer framework. The effectiveness of this Transformer-based SOH prediction method is demonstrated using public datasets, revealing that predictions for internal resistance and capacity closely align with actual values, with most RMSE values falling below 0.01. Furthermore, validation with an additional laboratory dataset confirms the accuracy and adaptability of our proposed approach, highlighting its potential to enhance SOH prediction in real-world applications.https://ieeexplore.ieee.org/document/11015565/Feature extractionlithium-ion batterySOH predictionTransformer
spellingShingle Tianfeng Long
Pengcheng Zhang
Xiaoqi Liu
Huaqing Shang
Meiling Yue
Xuesong Shen
Jianwen Meng
Improved SOH Prediction of Lithium-Ion Batteries Based on Multi-Dimensional Feature Analysis and Transformer Framework
IEEE Open Journal of Vehicular Technology
Feature extraction
lithium-ion battery
SOH prediction
Transformer
title Improved SOH Prediction of Lithium-Ion Batteries Based on Multi-Dimensional Feature Analysis and Transformer Framework
title_full Improved SOH Prediction of Lithium-Ion Batteries Based on Multi-Dimensional Feature Analysis and Transformer Framework
title_fullStr Improved SOH Prediction of Lithium-Ion Batteries Based on Multi-Dimensional Feature Analysis and Transformer Framework
title_full_unstemmed Improved SOH Prediction of Lithium-Ion Batteries Based on Multi-Dimensional Feature Analysis and Transformer Framework
title_short Improved SOH Prediction of Lithium-Ion Batteries Based on Multi-Dimensional Feature Analysis and Transformer Framework
title_sort improved soh prediction of lithium ion batteries based on multi dimensional feature analysis and transformer framework
topic Feature extraction
lithium-ion battery
SOH prediction
Transformer
url https://ieeexplore.ieee.org/document/11015565/
work_keys_str_mv AT tianfenglong improvedsohpredictionoflithiumionbatteriesbasedonmultidimensionalfeatureanalysisandtransformerframework
AT pengchengzhang improvedsohpredictionoflithiumionbatteriesbasedonmultidimensionalfeatureanalysisandtransformerframework
AT xiaoqiliu improvedsohpredictionoflithiumionbatteriesbasedonmultidimensionalfeatureanalysisandtransformerframework
AT huaqingshang improvedsohpredictionoflithiumionbatteriesbasedonmultidimensionalfeatureanalysisandtransformerframework
AT meilingyue improvedsohpredictionoflithiumionbatteriesbasedonmultidimensionalfeatureanalysisandtransformerframework
AT xuesongshen improvedsohpredictionoflithiumionbatteriesbasedonmultidimensionalfeatureanalysisandtransformerframework
AT jianwenmeng improvedsohpredictionoflithiumionbatteriesbasedonmultidimensionalfeatureanalysisandtransformerframework