SOC Estimation of Lithium-Ion Batteries Utilizing EIS Technology with SHAP–ASO–LightGBM

Accurate State of Charge (SOC) estimation is critical for optimizing the performance and longevity of lithium-ion batteries (LIBs), which are widely used in applications ranging from electric vehicles to renewable energy storage. Traditional SOC estimation methods, such as Coulomb counting and open-...

Full description

Saved in:
Bibliographic Details
Main Authors: Panpan Hu, Chun Yin Li, Chi Chung Lee
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Batteries
Subjects:
Online Access:https://www.mdpi.com/2313-0105/11/7/272
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850078231327145984
author Panpan Hu
Chun Yin Li
Chi Chung Lee
author_facet Panpan Hu
Chun Yin Li
Chi Chung Lee
author_sort Panpan Hu
collection DOAJ
description Accurate State of Charge (SOC) estimation is critical for optimizing the performance and longevity of lithium-ion batteries (LIBs), which are widely used in applications ranging from electric vehicles to renewable energy storage. Traditional SOC estimation methods, such as Coulomb counting and open-circuit voltage measurement, suffer from cumulative errors and slow response times. This paper proposes a novel machine learning-based approach for SOC estimation by integrating Electrochemical Impedance Spectroscopy (EIS) with the SHapley Additive exPlanations (SHAP) method, Atom Search Optimization (ASO), and Light Gradient Boosting Machine (LightGBM). This study focuses on large-capacity lithium iron phosphate (LFP) batteries (3.2 V, 104 Ah), addressing a gap in existing research. EIS data collected at various SOC levels and temperatures were processed using SHAP for feature extraction (FE), and the ASO–LightGBM model was employed for SOC prediction. Experimental results demonstrate that the proposed SHAP–ASO–LightGBM method significantly improves estimation accuracy, achieving an RMSE of 3.3%, MAE of 1.86%, and R<sup>2</sup> of 0.99, outperforming traditional methods like LSTM and DNN. The findings highlight the potential of EIS and machine learning (ML) for robust SOC estimation in large-capacity LIBs.
format Article
id doaj-art-0598dc43635f4bc4bf34df295bcffbe7
institution DOAJ
issn 2313-0105
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Batteries
spelling doaj-art-0598dc43635f4bc4bf34df295bcffbe72025-08-20T02:45:37ZengMDPI AGBatteries2313-01052025-07-0111727210.3390/batteries11070272SOC Estimation of Lithium-Ion Batteries Utilizing EIS Technology with SHAP–ASO–LightGBMPanpan Hu0Chun Yin Li1Chi Chung Lee2School of Science and Technology, Hong Kong Metropolitan University, Hong Kong SAR, ChinaSchool of Science and Technology, Hong Kong Metropolitan University, Hong Kong SAR, ChinaSchool of Science and Technology, Hong Kong Metropolitan University, Hong Kong SAR, ChinaAccurate State of Charge (SOC) estimation is critical for optimizing the performance and longevity of lithium-ion batteries (LIBs), which are widely used in applications ranging from electric vehicles to renewable energy storage. Traditional SOC estimation methods, such as Coulomb counting and open-circuit voltage measurement, suffer from cumulative errors and slow response times. This paper proposes a novel machine learning-based approach for SOC estimation by integrating Electrochemical Impedance Spectroscopy (EIS) with the SHapley Additive exPlanations (SHAP) method, Atom Search Optimization (ASO), and Light Gradient Boosting Machine (LightGBM). This study focuses on large-capacity lithium iron phosphate (LFP) batteries (3.2 V, 104 Ah), addressing a gap in existing research. EIS data collected at various SOC levels and temperatures were processed using SHAP for feature extraction (FE), and the ASO–LightGBM model was employed for SOC prediction. Experimental results demonstrate that the proposed SHAP–ASO–LightGBM method significantly improves estimation accuracy, achieving an RMSE of 3.3%, MAE of 1.86%, and R<sup>2</sup> of 0.99, outperforming traditional methods like LSTM and DNN. The findings highlight the potential of EIS and machine learning (ML) for robust SOC estimation in large-capacity LIBs.https://www.mdpi.com/2313-0105/11/7/272lithium-ion batteriesstate of chargeelectrochemical impedance spectroscopySHAPLightGBMatom search optimization
spellingShingle Panpan Hu
Chun Yin Li
Chi Chung Lee
SOC Estimation of Lithium-Ion Batteries Utilizing EIS Technology with SHAP–ASO–LightGBM
Batteries
lithium-ion batteries
state of charge
electrochemical impedance spectroscopy
SHAP
LightGBM
atom search optimization
title SOC Estimation of Lithium-Ion Batteries Utilizing EIS Technology with SHAP–ASO–LightGBM
title_full SOC Estimation of Lithium-Ion Batteries Utilizing EIS Technology with SHAP–ASO–LightGBM
title_fullStr SOC Estimation of Lithium-Ion Batteries Utilizing EIS Technology with SHAP–ASO–LightGBM
title_full_unstemmed SOC Estimation of Lithium-Ion Batteries Utilizing EIS Technology with SHAP–ASO–LightGBM
title_short SOC Estimation of Lithium-Ion Batteries Utilizing EIS Technology with SHAP–ASO–LightGBM
title_sort soc estimation of lithium ion batteries utilizing eis technology with shap aso lightgbm
topic lithium-ion batteries
state of charge
electrochemical impedance spectroscopy
SHAP
LightGBM
atom search optimization
url https://www.mdpi.com/2313-0105/11/7/272
work_keys_str_mv AT panpanhu socestimationoflithiumionbatteriesutilizingeistechnologywithshapasolightgbm
AT chunyinli socestimationoflithiumionbatteriesutilizingeistechnologywithshapasolightgbm
AT chichunglee socestimationoflithiumionbatteriesutilizingeistechnologywithshapasolightgbm