Hybrid Physics–AI Digital Twin for BESS
Vietnam’s first Hybrid Physics–AI Digital Twin platform for Battery Energy Storage Systems, integrating electrochemical aging models, CFD-derived thermal prediction, and AI diagnostics to improve safety, battery lifetime, and renewable-energy deployment.
THE CHALLENGE
Battery Energy Storage Systems in Vietnam require early detection of degradation, thermal runaway risks, uneven module aging, and operational anomalies, particularly under tropical climate conditions, renewable intermittency, and EV charging stress.
THE SOLUTION
The project develops a hybrid physics–AI digital twin platform that combines real-time BESS telemetry, electrochemical aging models, electro-thermal CFD, reduced-order thermal prediction, virtual sensing, and uncertainty-aware anomaly detection to improve battery health monitoring, thermal safety, and deployment readiness.
DIGITAL TWIN
FRAMEWORK
STRATEGIC OBJECTIVES
Develop hybrid physics–AI digital twin for BESS under tropical operating conditions
Establish manufacturer-agnostic BESS–EVCS design basis and operational datasets
Integrate telemetry with electrochemical degradation, thermal, and safety models
Build reduced-order and physics-informed AI predictive models for SoH/RUL and temperature
Provide early anomaly warning and thermal safety diagnostics
Deploy cloud-edge digital twin platform for real-time operational support