The project began with a successful Kick-off Meeting, where consortium partners gathered to establish a common vision, strengthen collaboration, and set the foundations for the successful achievement of the project objectives.

The main challenge addressed by AI4EAFRoute is the management of the high complexity and variability of Electric Arc Furnace (EAF) operations, where harsh operating conditions, fluctuating scrap quality, and limited visibility of critical process parameters can negatively affect productivity, equipment reliability, energy efficiency, and safety. Traditional monitoring and maintenance approaches often rely on fragmented data and reactive interventions, making it difficult to predict failures, optimize process performance, and prevent operational disruptions. To overcome these challenges, the project aims to integrate advanced sensing technologies, artificial intelligence models, and decision support tools capable of transforming large volumes of heterogeneous industrial data into actionable information for real-time operational control, predictive maintenance, safety management, and sustainable steel production.