Model predictive control of the refining stage in an electric arc furnace using soft sensorsBlažič, Aljaž (Avtor) Škrjanc, Igor (Avtor) Logar, Vito (Avtor) model predictive controlbath temperatureelectric arc furnacedissolved oxygenIn this paper, a novel Model Predictive Control (MPC) based on soft sensors is developed to optimize the refining stage in Electric Arc Furnaces (EAFs). Given the significant energy consumption and environmental impact associated with EAF operations, there is a critical need for more precise and efficient control strategies. The proposed MPC approach utilizes real-time soft sensors to accurately determine critical parameters, i.e., bath temperature and dissolved oxygen content. By replacing operators’ subjective judgments with continuous, data-driven feedback, this methodology facilitates precise control adjustments throughout the refining process. The implementation of this MPC has shown that the duration of the refining stage has been reduced by approximately 80 seconds, which directly translates into shorter tap-to-tap times, lower energy consumption and improved operational efficiency. In addition, consistently maintaining optimal bath conditions ensures improved steel quality, greater reliability, and higher overall productivity of the EAF process.20252025-09-08 10:18:16Članek v reviji172523UDK: 621.365.2:681.5ISSN pri članku: 1742-6596DOI: 10.1088/1742-6596/3050/1/012010COBISS_ID: 246338563OceCobissID: 246334211sl