Jiangshan Zhang

In the continuous casting process, the flow velocity of molten steel at the surface of the mold directly influences the melting of the flux, slag entrainment behavior, and the uniformity of heat transfer. Fast and accurate prediction of the magnitude and distribution of surface-flow velocity is crucial for defect suppression and ensuring continuous casting quality. In this study, a three-dimensional electromagnetic–fluid dynamic coupled model was established and validated to simulate the molten steel flow behavior under various casting speeds, Electromagnetic Stirring (EMS) currents, EMS frequencies, and Submerged Entry Nozzle (SEN) immersion depth. Subsequently, the maximum surface velocity in the mold was fitted to derive a predictive formula under different conditions; the median range and width of the surface high-velocity range were predicted in a similar way. As a result, a regression model derived from Computational Fluid Dynamics (CFD) was built to predict the maximum mold surface velocity and the high-velocity range within milliseconds. The reliability of the regression model was verified by newly generated simulation results, with the relative error between the predicted and simulated maximum surface velocities kept within 2%. It was shown that the maximum surface velocity increases with casting speed and EMS current but decreases with EMS frequency. The median range of the high-velocity range decreases with increasing casting speed and current. The immersion depth of SEN had a minimal impact on the maximum surface velocity in the mold and the high-velocity range. This regression model is beneficial for rapid mold design and for predicting potential slag entrainment, breakout risks, and billet defects, for the purpose of intelligent continuous casting.

Accurate prediction of activity in multi-component slag systems is of great significance for optimizing metallurgical processes. Existing models, which include both thermodynamic calculations and neural networks, often rely on simplifying assumptions or require extensive hyperparameter tuning. In addition, the experimental acquisition of slag activity data is difficult due to high-temperature conditions and complex procedures, resulting in limited and scarce data. To address these limitations, a novel model was proposed integrating TabPFN and SHAP analysis for activity prediction on small data. Model performance was benchmarked against existing models, and the results show that TabPFN not only surpasses other models in terms of predictive accuracy but also enables enhanced explainability by SHAP analysis. The TabPFN model achieved an R2 of 0.9816, an RMSE of 0.0451, an MAE of 0.0243, and a model response time of 0.21 s. Moreover, a SiO2 activity prediction tool was developed, featuring user-friendly operation, fast computation, and automatic model updating without the need for extensive hyperparameter tuning when new data are introduced, offering practical value for industrial deployment. This work provides a data-driven and interpretable approach for the real-time and accurate prediction of slag activity under complex process conditions.

Ladle furnace (LF) refining is one of the most widely used secondary refining processes for producing clean steel and constitutes a key process in the steelmaking–continuous casting section. The properties of slag play a decisive role in determining molten steel quality and refining efficiency. In this study, based on the composition of refining slag from a steelmaking plant in China, the properties of a CaO-SiO₂-MgO-Al₂O₃ slag system were investigated with respect to five aspects, the liquid phase region, sulphide capacity, melting properties, slag viscosity, and mineralogical phase precipitation, at varying temperatures, basicity, w(MgO) and w(Al₂O₃) using FactSage and the KTH model. Analysis of the slag properties indicates that the CaO-SiO₂-MgO-Al₂O₃ slag system performs better when basicity ranges from 3 to 4, w(MgO) is between 6% and 8%, and w(Al₂O₃) is 15%–25%. These findings provide theoretical support and guidance for optimizing the refining slag system in plant trials.

In this study, the decarburization behavior in basic oxygen furnace (BOF) steelmaking was investigated based on the multi-zone reaction mechanism. The contributions of the main reaction zones to decarburization were clarified, and the effects of key factors—including the effective reaction amount in the main reaction zones, the post combustion ratio (PCR) in auxiliary reaction zones, and the carbon content of scrap steel—on decarburization behavior were quantitatively analyzed. The results indicate that decarburization predominantly occurs in the jet impact reaction zone (approximately 76% of the total decarburization), followed by the emulsion and metal droplet reaction zone (approximately 14%) and the bulk metal and slag reaction zone (approximately 10%). Variations in the effective reaction amount for the main reaction zones significantly affect both the decarburization rate and the endpoint carbon content, with the direct oxidation decarburization reaction in the jet impact reaction zone being the dominant factor. In addition, the PCR in the gas homogenization zone of the auxiliary reaction zones determines the distribution ratio of effective reaction oxygen, while the melting behavior of scrap steel in the metal homogenization zone plays a critical role in the precise control of the endpoint carbon content. This study provides a quantitative elucidation of the effects of different reaction zones on decarburization behavior, offering a foundation for the precise control of endpoint carbon content in BOF steelmaking.