Consortium
The consortium combines the expertise of technology providers, academic institutions, and major European steelmakers to accelerate the digital transformation of the steel industry. By integrating cutting-edge research with real industrial environments, the partnership creates a strong ecosystem for developing, validating, and scaling innovative AI-driven solutions for EAF operations.
RINA Consulting – Centro Sviluppo Materiali S.p.A (RINA-CSM)
RINA-CSM serves as the Project Coordinator of AI4EAFRoute, leading project management, the development of the AI-based Decision Support System, and all dissemination and exploitation activities. RINA-CSM also contributes to advanced monitoring technologies and AI-driven solutions designed to improve the efficiency, reliability, safety, and sustainability of Electric Arc Furnace operations.
VDEh-Betriebsforschungsinstitut GmbH (BFI)
BFI contributes its expertise in steel process research, sensor-based monitoring, data analytics, and AI applications for Electric Arc Furnaces. The institute supports the development, validation, and industrial assessment of advanced monitoring and decision-support tools aimed at improving EAF efficiency, reliability, safety, and sustainability.
Rheinisch-Westfälische Technische Hochschule Aachen (RWTH)
RWTH is responsible for designing and developing the core AI algorithms of AI4EAFRoute. RWTH develops advanced machine learning models for scrap melting management, electrical arc optimization, component condition monitoring, event detection, and overall EAF performance analysis, transforming industrial sensor data into predictive tools that improve process efficiency, reliability, and sustainability.
Feralpi acts as the main industrial demonstrator and leader of the sensor development and data collection activities. The company provides the industrial environment for testing and validating advanced monitoring systems, AI models, and Decision Support System functionalities aimed at improving EAF efficiency, reliability, safety, and sustainability.
SIDENOR I+D leads the assessment of the industrial, economic, and environmental impacts of the AI4EAFRoute solutions. The organization contributes to the development and validation of AI-based monitoring and decision-support tools while evaluating their effects on process performance, plant reliability, maintenance strategies, and CO₂ emissions in Electric Arc Furnace operations.
University of Ljubljana - Faculty of electrical engineering (UL)
UL contributes its expertise in control systems, automation, and process modelling to develop advanced solutions for EAF electrical management. UL supports the development of the Arc Quality Index (AQI), high-frequency data analysis, and AI-based control strategies aimed at improving arc stability, energy efficiency, and overall furnace performance. It also contributes to the integration of these solutions into the project’s decision support framework.
SIJ Acroni provides the industrial validation environment for AI4EAFRoute and contributes operational expertise in EAF steelmaking. The company supports data collection, testing of advanced monitoring systems, and validation of AI-based solutions for process optimization, electrical management, and predictive maintenance under real industrial conditions.
SIJ Storitve contributes to the development, testing, and industrial validation of advanced monitoring and AI-based solutions for Electric Arc Furnace operations. As part of the SIJ Group, it supports data collection, process analysis, and the assessment of innovative tools aimed at improving equipment reliability, operational efficiency, and sustainability in steel production