Paper Title: Data-Driven Battery Digital Twin in Unreal Engine
Conference Name: Korean Institute of Communications and Information Sciences (KICS Summer 2023)
Abstract: This paper proposes a data-driven digital twin framework for battery management systems. The proposed employed a gated recurrent unit neural network, to predict the battery state of charge (SoC) based on input parameters such as voltage, current, and temperature. The resulting predictions are visualized in the Unreal Engine interface, allowing for real-time monitoring. The model achieved a mean absolute error of 1.31%, 1.11%, and 0.71% at temperatures of 0°C, 10°C, and 25°C respectively. This system has potential applications in metaverse-based condition monitoring and battery management.
Status: Accepted
Conference Type: Domestic
Cite: Paul Michael Custodio, Robin Matthew Medina, Judith Nkechinyere Njoku, Cosmas Ifeanyi Nwakanma, Jae-Min Lee, Dong-Seong Kim "Data-Driven Battery Digital Twin in Unreal Engine", Korean Institute of Communications and Information Sciences (KICS Summer 2023) Conference, Ramada Plaza, Jeju Island, Korea