Ladle Furnace Slag Characterization Through Hyperspectral Reflectance Regression Model for Secondary Metallurgy Process Optimization

In steelmaking process, close control of slag evolution is as important as control of steel composition. However, to date, there are no industrially consolidated techniques that allow us fast and
in-situ
analysis of the chemical composition of the slag, as in the case of steel with optical emission spectrometer spectrometers. In this work, a method to analyze spectral reflectance of ladle furnace slag samples to estimate their composition is proposed. This method does not require sample preprocessing and is based on a regression algorithm that mathematically maps the spectral reflectance of the slag with its actual composition with errors lower than 10%. Specifically designed normalization and calibration steps have been proposed to allow us a global model training with data from different locations. This allows us real-time monitoring of the thermo-dynamical state of the steel process by feeding a thermodynamic equilibrium optimization model. The optimizer minimizes the cost to reach the target steel quality with lower energy and additive costs. The system has been validated on several ArcelorMittal locations achieving process savings of 0.71 € per liquid steel tons.