This seminar introduces the latest research trends in explainable artificial intelligence (XAI) for next-generation Battery Management Systems (BMS). As lithium-ion batteries are increasingly deployed in electric vehicles and energy storage systems, the importance of accurately and reliably estimating and managing battery states continues to grow.

The speaker, Prof. Tedjani Mesbahi, conducts research on BMS using physics-based models, data-driven models, and hybrid approaches that consider the electrochemical, thermal, and aging characteristics of batteries. In this talk, he will present methods for state-of-X estimation, degradation modeling, and fault diagnosis, as well as approaches that integrate AI techniques with physics-based models to enhance explainability and trustworthiness.

He will also present real-world research cases and experimental results from the European H2020 ENERGETIC project. The talk will further discuss the current development of next-generation BMS for electric vehicles and energy storage systems, and explore the convergence of battery physics, data-driven intelligence, industrial applications, and regulatory requirements.

We warmly invite everyone interested in battery systems, artificial intelligence, energy storage technologies, and electric vehicles to attend.

Date: June 25 (Thursday), 16:00–17:00
Venue: Haedong Information Room (2F), Central Conference Building, Mechanical Engineering Building (N7), KAIST Main Campus

Speaker: Prof. Tedjani Mesbahi (INSA Strasbourg)
Title: From Black Box to Glass Box: Explainable AI for Next-Generation Battery Management Systems