Optimizing Lithium-Ion Battery Performance: Integrating Machine Learning and Explainable AI for Enhanced Energy Management

Basit Öğe Kaydı
dc.authoridoyucu, saadin/0000-0003-3880-3039
dc.authoridBicer, Emre/0000-0002-9871-4102
dc.authoridSAGIROGLU, SEREF/0000-0003-0805-5818
dc.authoridAKSOZ, Ahmet/0000-0002-2563-1218
dc.authoridErsoz, Betul/0000-0001-6221-1530
dc.contributor.authorOyucu, Saadin
dc.contributor.authorErsoz, Betul
dc.contributor.authorSagiroglu, Seref
dc.contributor.authorAksoz, Ahmet
dc.contributor.authorBicer, Emre
dc.date.accessioned2024-10-26T18:09:13Z
dc.date.available2024-10-26T18:09:13Z
dc.date.issued2024
dc.departmentSivas Cumhuriyet Üniversitesi
dc.description.abstractManaging the capacity of lithium-ion batteries (LiBs) accurately, particularly in large-scale applications, enhances the cost-effectiveness of energy storage systems. Less frequent replacement or maintenance of LiBs results in cost savings in the long term. Therefore, in this study, AdaBoost, gradient boosting, XGBoost, LightGBM, CatBoost, and ensemble learning models were employed to predict the discharge capacity of LiBs. The prediction performances of each model were compared based on mean absolute error (MAE), mean squared error (MSE), and R-squared values. The research findings reveal that the LightGBM model exhibited the lowest MAE (0.103) and MSE (0.019) values and the highest R-squared (0.887) value, thus demonstrating the strongest correlation in predictions. Gradient boosting and XGBoost models showed similar performance levels but ranked just below LightGBM. The competitive performance of the ensemble model indicates that combining multiple models could lead to an overall performance improvement. Furthermore, the study incorporates an analysis of key features affecting model predictions using SHAP (Shapley additive explanations) values within the framework of explainable artificial intelligence (XAI). This analysis evaluates the impact of features such as temperature, cycle index, voltage, and current on predictions, revealing a significant effect of temperature on discharge capacity. The results of this study emphasize the potential of machine learning models in LiB management within the XAI framework and demonstrate how these technologies could play a strategic role in optimizing energy storage systems.
dc.description.sponsorshipEuropean Union's Horizon Europe research and innovation programme under Next Generation of Multifunctional, Modular and Scalable Solid State Batteries System (EXTENDED); Battery Research Group at Sivas University of Science and Technology (SBTU)
dc.description.sponsorshipThis research was conducted collaboratively by the MOBILERS team at Sivas Cumhuriyet University and the Battery Research Group at Sivas University of Science and Technology (SBTU).
dc.identifier.doi10.3390/su16114755
dc.identifier.issn2071-1050
dc.identifier.issue11
dc.identifier.scopus2-s2.0-85195865522
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.3390/su16114755
dc.identifier.urihttps://hdl.handle.net/20.500.12418/29991
dc.identifier.volume16
dc.identifier.wosWOS:001245672000001
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherMdpi
dc.relation.ispartofSustainability
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectLi-ion
dc.subjectBMS
dc.subjectSoH estimation
dc.subjectensemble learning
dc.subjectexplainable AI
dc.subjectSHAP
dc.titleOptimizing Lithium-Ion Battery Performance: Integrating Machine Learning and Explainable AI for Enhanced Energy Management
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu