Bayesian information criterion based data-driven state of charge estimation for lithium-ion battery

Accurate state of charge (SOC) estimation is essential for the safe and reliable operation of Li-ion batteries. To solve the problem of poor generalisation caused by over-fitting, this paper presents a combination algorithm based on feature selection to estimate battery SOC. Firstly, a portion of th...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of energy storage Jg. 55; S. 105669
Hauptverfasser: Liu, Xingtao, Yang, Jiacheng, Wang, Li, Wu, Ji
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 30.11.2022
Schlagworte:
Bayesian information criterion
Data-driven
Lithium-ion battery
State of charge estimation
Support vector regression algorithm
Lithium-ion battery
State of charge estimation
Data-driven
Bayesian information criterion
Support vector regression algorithm
ISSN:2352-152X, 2352-1538
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Accurate state of charge (SOC) estimation is essential for the safe and reliable operation of Li-ion batteries. To solve the problem of poor generalisation caused by over-fitting, this paper presents a combination algorithm based on feature selection to estimate battery SOC. Firstly, a portion of the features is extracted from the extended Kalman filtering (EKF) results. It forms the set of features to be selected with four other measured features. Secondly, the optimal feature subset is adopted by designing a wrapped feature screening framework based on the Bayesian information criterion (BIC). Finally, the selected combination of features is adopted to train the support vector regression (SVR) model, which is applied to the battery SOC estimation. The experimental results reveal that the combination strategy of EKF and SVR improves the accuracy of SOC estimation. The optimal SVR model based on the feature selection criterion shows better generalisation. Better estimation results in four driving conditions are achieved, and the root-mean-square error of the battery SOC estimation is decreased by at least 64.1 % and 56.5 % compared to the EKF algorithm and SVR algorithm driven by full feature, respectively. •Three features are extracted from SOC estimation results of the EKF.•The average current and average terminal voltage are used as features.•Bayesian information criterion is used to determine the optimal features subset.•The EKF algorithm is combined with the SVR algorithm to estimate SOC.
ISSN:2352-152X
2352-1538
DOI:10.1016/j.est.2022.105669