Physics and Knowledge Transfer-based Cognitive Digital Twin for Advanced Battery Analytics

Avatar for Wei ZHANG
Wei ZHANG    
Associate Professor

Read More 

This project develops next-generation battery analytics using cognitive digital twins and physics-based machine learning to create accurate, explainable models that integrate both data-driven and physics-based approaches.

This novel approach seeks to enable advanced battery management systems with significant economic and sustainability benefits for industries requiring reliable battery performance monitoring.

Project Deliverables/Outcomes/Impact
  • Physics-informed neural networks (PINNs).
  • Generalised machine learning algorithms validated across diverse battery chemistries and operating conditions.
  • Advanced battery management systems for electric vehicles and energy storage applications with edge intelligence.
     

 

Diagram of a Physics-Informed Neural Network (PINN) architecture for battery health monitoring. It shows physical knowledge and simulation data being integrated into a backbone neural network model to predict State of Health (SOH) and Remaining Useful Life (RUL).