Top-bottom combined blowing converter steelmaking involves complex thermodynamic and kinetic processes, and predictive modeling has long been a key focus in steelmaking research. This paper proposes a kinetic process prediction model with on-site applicability. Based on actual production data, machine learning models (BP neural network, random forest, XGBoost) are employed to predict Tapping Steel Oxygen (TSO) content, which is then used as input for the kinetic model. An optimized theoretical decarburization kinetic model is selected and validated against measured Tapping Steel Carbon (TSC) data. The key innovation lies in the integration of converter control parameters into the kinetic model through a data-driven cyclic iteration algorithm. Comparison of prediction accuracy before and after integration shows that the model’s TSC prediction within the range [−0.2, +0.2] improves by 6.26%. This work presents a novel approach for enhancing kinetic models via control parameter integration, offering effective guidance for real-time monitoring and optimization in converter steelmaking.

Top-bottom combined blowing converter steelmaking involves complex thermodynamic and kinetic processes.The development and application of predictive models for the converter smelting process have long been a focal point in steelmaking research.This paper establishes a kinetic process prediction model for converter steelmaking that can provide on-site guidance. Initially,based on actual production data and real field conditions from a specific company, machine learning models—including BP neural networks,random forests,and XGBoost—are coupled to predict the Tapping Steel Oxygen (TSO) composition for each heat in the production process.The prediction results serve as inputs for the kinetic model.Subsequently,existing kinetic models are analyzed,and an optimized theoretical kinetic model for the converter steelmaking process is selected.The accuracy of this kinetic model is evaluated using measured Tapping Steel Carbon (TSC) data.Finally,a data cyclic iteration algorithm is employed to integrate converter control parameters into the theoretical model of decarburization kinetics.By comparing the prediction accuracy of the decarburization kinetic model before and after incorporating control parameters,the effectiveness of integrating control parameters into the theoretical model is validated.Evaluation results of the decarburization kinetic model’s prediction accuracy show that,after incorporating control parameters,the prediction accuracy of TSC carbon content within the range [-0.2, +0.2] improved by 6.26%.This study provides a new approach for optimizing converter kinetic process prediction models and offers significant guidance for real-time monitoring and adjustment in production practice.