Abstract
Advancements in battery management systems involve using digital twins to optimize battery performance in electric vehicles. The state of charge and state of health estimations is essential for battery efficiency and longevity. Digital twins allow for precise predictions of the state of charge and state of health by simulating battery behavior under different conditions. Using artificial intelligence in digital twins, as demonstrated through studies employing deep neural networks and long short-term memory networks, improves predictive capabilities. However, incorporating artificial intelligence presents challenges due to the opaque nature of the models, necessitating the need for explainable artificial intelligence and trustworthy digital twin models. This study pioneered explainable artificial intelligence methods such as SHapley Additive exPlanations, Local Interpretable Model-agnostic Explanations, and linear regression-based surrogate models to explain the predictions of deep neural networks and long short-term memory networks in digital twin-supported battery management systems. The results reveal that the long short-term memory digital twin model is more reliable due to a higher R 2 score and lower mean residuals.
Funding Information
  • Innovative Human Resource Development for Local Intellectualization Program through the Institute for Information and Communications Technology Planning
  • Korean Government [Ministry of Science and Information and Communication Technology (ICT)] (IITP-2024-2020-0-01612, (50%))
  • Priority Research Centers Program through the National Research Foundation, South Korea
  • Ministry of Education, Science and Technology (2018R1A6A1A03024003, (50%))

This publication has 42 references indexed in Scilit: