State of charge estimation for lithium-ion batteries based on cross-domain transfer learning with feedback mechanism

When the deep learning model is applied to estimate battery state of charge (SOC), the information inside the training set cannot be leveraged thoroughly, which would cause poor SOC estimation accuracy and robustness on the testing set. To solve the problem, this paper proposes an adaptive convoluti...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of energy storage 2023-10, Vol.70, p.108037, Article 108037
Hauptverfasser: Yang, Yongsong, Zhao, Lijun, Yu, Quanqing, Liu, Shizhuo, Zhou, Guanghui, Shen, Weixiang
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:When the deep learning model is applied to estimate battery state of charge (SOC), the information inside the training set cannot be leveraged thoroughly, which would cause poor SOC estimation accuracy and robustness on the testing set. To solve the problem, this paper proposes an adaptive convolutional neural network-gated recurrent unit with Kalman filter and feedback mechanism (Fb-Ada-CNN-GRU-KF) for SOC estimation considering distribution difference of data segments inside the training set through transfer learning and extracting the spatial information through convolutional layer. Furthermore, the feedback mechanism provides the model more information to learn to correct the systematic error, and the KF in the proposed model works as a post data processor to obtain a steady and smooth SOC estimation results. Experimental and comparison results show that the proposed model for SOC estimation outperforms the existing deep learning methods in terms of the accuracy, generalization and stability. •Ada-CNN-GRU model with transfer learning is proposed and firstly applied for battery SOC estimation.•Both the segments' distribution difference and spatial features of the training dataset are taken into consideration.•An error feedback mechanism is proposed to reduce systematic prediction error.•KF is leveraged as a post processing machine to eliminate the abnormal prediction value.•The accuracy and robustness of the proposed method for SOC estimation are verified.
ISSN:2352-152X
2352-1538
DOI:10.1016/j.est.2023.108037