TY  - JOUR
T1  - HyBaTwin: Web-Based Hybrid Digital Twin Platform for Electric Vehicle Battery Capacity Estimation
AU  - Njoku, Judith Nkechinyere 
AU  - Eneh, Anthony Uchenna 
AU  - Nwakanma, Cosmas Ifeanyi 
AU  - Lee, Jae-Min 
AU  - Kim, Dong-Seong 
JO  - The Journal of Korean Institute of Communications and Information Sciences
PY  - 2025
DA  - 2025/1/1
DO  - 10.7840/kics.2025.50.4.549
KW  - digital twin
KW  - AI-based
KW  - electric vehicles
KW  - capacity estimation
KW  - battery management system
AB  - This study presents early results of a web-based digital twin (DT) for battery management systems (BMS).
The proposed DT explores a hybrid of model-based and data-driven approaches, enabling the exploitation of each approach’s distinctive merits and constraints. Experiments employing explainable artificial intelligence (XAI) techniques were undertaken to select the most trustworthy and explainable approach to be deployed to a web server. First, a model-based DT was developed using physics based modelling and AI to achieve the hybrid model. Next, four models, including a deep neural network, a long-short-term memory network, a graph neural network (GNN), and a transformer neural network (TNN) model, were independently trained to minimize the residual between the actual battery data and the prediction of the model-based DT. All hybrid DT models were assessed based on mean squared error, latency, and prediction confidence. With the best confidence score of 98.255% and lowest latency of 0.079, the hybrid GNN DT model emerged as the best, demonstrating the viability of the proposed explainable hybrid approach in approximating actual battery behavior and the utility of a web-based DT.