An optimization framework for hot-rolled strip crown control based on model-driven digital twin

Accurate crown control is paramount for ensuring the quality of hot-rolled strip products. Given the multitude of influencing parameters and the intricate coupling and genetic relationships among them, the conventional crown control method is no longer sufficient to meet the precision requirements of schedule-free rolling. To address this limitation, an optimization framework for hot-rolled strip crown control was developed based on model-driven digital twin (MDDT). This framework enhances the strip crown control precision by facilitating collaborative operations among physical entities, virtual models, and functional application layers. In virtual modeling, a data-driven approach that integrates the extreme gradient boosting and the improved Harris hawk optimization algorithm was firstly proposed to fit the relationship between key process parameters and strip crown, and a global–local collaborative training strategy was proposed to enhance the model adaptability to diverse working conditions. Subsequently, the influence of crucial process factors on the virtual model was examined through model responses. Furthermore, a novel optimization mode for crown control based on MDDT was established by aligning and reconstructing both the physical and virtual models, thereby enhancing the crown control precision. Finally, data trials were conducted to validate the effectiveness of the proposed framework. The results indicated that the proposed method exhibited satisfactory performance and could be effectively utilized to improve the crown control precision.