EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Battery State of Charge Estimation Based on Improved Neural Network

Hong Zhang

Journal of Computer Science and Artificial Intelligence · 11.02.2025 · 2 (1) · 36-44

DOI: 10.54097/9ervp336 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computer Science and Artificial Intelligence, online erschienen am 11.02.2025. Verfasst von Hong Zhang. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of battery state of charge (SOC) is vital for extending battery lifespan and ensuring operational safety in electric vehicles. However, traditional approaches exhibit constrained predictive accuracy and robustness under complex environments and variable operating conditions. Therefore, this study proposes the AO-BiGRU-CAM model, integrating Aquila Optimization (AO), a bidirectional Gated Recurrent Units (BiGRU), and a channel attention mechanism (CAM). It refines parameter search while enhancing focus on salient features to improve training efficiency and predictive accuracy. Under diverse temperatures and drive cycles, AO-BiGRU-CAM reduces errors by approximately 5%–10% in MSE, RMSLE, and MAPE compared with other models, demonstrating robust adaptability.

Zitieren

APA

Zhang, H. (2025). Battery State of Charge Estimation Based on Improved Neural Network. Journal of Computer Science and Artificial Intelligence, 2(1), 36-44. https://doi.org/10.54097/9ervp336

Vancouver

Zhang H. Battery State of Charge Estimation Based on Improved Neural Network. Journal of Computer Science and Artificial Intelligence. 2025;2(1):36-44. doi:10.54097/9ervp336

BibTeX
@article{Zhang2025,
  author = {Zhang, Hong},
  title = {Battery State of Charge Estimation Based on Improved Neural Network},
  journal = {Journal of Computer Science and Artificial Intelligence},
  year = {2025},
  volume = {2},
  number = {1},
  pages = {36--44},
  doi = {10.54097/9ervp336}
}
Kostenlos starten →