Elias’ research focuses on the applications of machine learning in the optimal operation and health monitoring of battery-powered assets. Specifically, Elias analyses historical data of battery performance relating to applications in the electrified transport and grid energy storage sectors using deep learning methods. Through the processing of signals produced during equipment operation he aims to formulate adaptive multi-objective control strategies, prognosticate performance fade and diagnose faults. He is a mechanical engineer and a chartered member of the Engineering Council.