Prediction of Lithium-Ion Battery Health Using GRU-BPP

Accurate prediction of lithium-ion batteries’ (LIBs) state-of-health (SOH) is crucial for the safety and maintenance of LIB-powered systems. This study addresses the variability in degradation trajectories by applying gated recurrent unit (GRU) networks alongside principal component analysis (PCA),...

Full description

Saved in:
Bibliographic Details
Main Authors: Sahar Qaadan, Aiman Alshare, Alexander Popp, Benedikt Schmuelling
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Batteries
Subjects:
Online Access:https://www.mdpi.com/2313-0105/10/11/399
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850145133889060864
author Sahar Qaadan
Aiman Alshare
Alexander Popp
Benedikt Schmuelling
author_facet Sahar Qaadan
Aiman Alshare
Alexander Popp
Benedikt Schmuelling
author_sort Sahar Qaadan
collection DOAJ
description Accurate prediction of lithium-ion batteries’ (LIBs) state-of-health (SOH) is crucial for the safety and maintenance of LIB-powered systems. This study addresses the variability in degradation trajectories by applying gated recurrent unit (GRU) networks alongside principal component analysis (PCA), Granger causality, and K-means clustering to analyze the relationships between operating conditions—such as temperature and load profiles—and battery performance degradation. This paper uses a publicly accessible dataset derived by aging three prismatic LIB cells under a realistic forklift operation profile. First, we identify the features that are relevant to driving variance, then we employ the winning algorithm of K-means clustering for the classification of operational states. Granger causality later investigates the inter-group relationships. Our GRU-BPP model achieves an RMSE value of 0.167 and an MAE of 0.129 for the reference performance testing (RPT) dataset and an RMSE of 0.032 with an MAE of 0.025 for the aging dataset, thus outperformed benchmark methods such as GRU, LME, and XGBoost. These results further enhance the predictiveness and robustness of this approach and yield a holistic solution to the conventional challenges in battery management and their remaining useful life (RUL) predictions.
format Article
id doaj-art-ab44935927504f77b72440cbb9ef2aa4
institution OA Journals
issn 2313-0105
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Batteries
spelling doaj-art-ab44935927504f77b72440cbb9ef2aa42025-08-20T02:28:10ZengMDPI AGBatteries2313-01052024-11-01101139910.3390/batteries10110399Prediction of Lithium-Ion Battery Health Using GRU-BPPSahar Qaadan0Aiman Alshare1Alexander Popp2Benedikt Schmuelling3Mechatronics Engineering, German Jordanian University, Madaba Street, Amman 11180, JordanMechanical and Maintenance Engineering, German Jordanian University, Madaba Street, Amman 11180, JordanInstitute of Electric Mobility and Energy Storage Systems, University of Wuppertal, Rainer-Gruenter-Str. 21, 42119 Wuppertal, GermanyInstitute of Electric Mobility and Energy Storage Systems, University of Wuppertal, Rainer-Gruenter-Str. 21, 42119 Wuppertal, GermanyAccurate prediction of lithium-ion batteries’ (LIBs) state-of-health (SOH) is crucial for the safety and maintenance of LIB-powered systems. This study addresses the variability in degradation trajectories by applying gated recurrent unit (GRU) networks alongside principal component analysis (PCA), Granger causality, and K-means clustering to analyze the relationships between operating conditions—such as temperature and load profiles—and battery performance degradation. This paper uses a publicly accessible dataset derived by aging three prismatic LIB cells under a realistic forklift operation profile. First, we identify the features that are relevant to driving variance, then we employ the winning algorithm of K-means clustering for the classification of operational states. Granger causality later investigates the inter-group relationships. Our GRU-BPP model achieves an RMSE value of 0.167 and an MAE of 0.129 for the reference performance testing (RPT) dataset and an RMSE of 0.032 with an MAE of 0.025 for the aging dataset, thus outperformed benchmark methods such as GRU, LME, and XGBoost. These results further enhance the predictiveness and robustness of this approach and yield a holistic solution to the conventional challenges in battery management and their remaining useful life (RUL) predictions.https://www.mdpi.com/2313-0105/10/11/399model performance testgated recurrent unitstate of healthGranger causality analysisclusteringprincipal component analysis
spellingShingle Sahar Qaadan
Aiman Alshare
Alexander Popp
Benedikt Schmuelling
Prediction of Lithium-Ion Battery Health Using GRU-BPP
Batteries
model performance test
gated recurrent unit
state of health
Granger causality analysis
clustering
principal component analysis
title Prediction of Lithium-Ion Battery Health Using GRU-BPP
title_full Prediction of Lithium-Ion Battery Health Using GRU-BPP
title_fullStr Prediction of Lithium-Ion Battery Health Using GRU-BPP
title_full_unstemmed Prediction of Lithium-Ion Battery Health Using GRU-BPP
title_short Prediction of Lithium-Ion Battery Health Using GRU-BPP
title_sort prediction of lithium ion battery health using gru bpp
topic model performance test
gated recurrent unit
state of health
Granger causality analysis
clustering
principal component analysis
url https://www.mdpi.com/2313-0105/10/11/399
work_keys_str_mv AT saharqaadan predictionoflithiumionbatteryhealthusinggrubpp
AT aimanalshare predictionoflithiumionbatteryhealthusinggrubpp
AT alexanderpopp predictionoflithiumionbatteryhealthusinggrubpp
AT benediktschmuelling predictionoflithiumionbatteryhealthusinggrubpp