The cross-sectional profile of hot-rolled silicon steel strips has a great impact on the transverse thickness difference of cold-rolled strips. The genetic algorithm - Levenberg Marquardt - backpropagation neural network model was developed for the analysis of heredity effect of the cross-sectional profile of hot-rolled strip. The feature importance was analysed based on random forest and extreme gradient boosting methods. Furthermore, the influence law was analysed by data visualization. The coupling term of the strip crown and thickness , the edge drop and the coupling term of the strip wedge and thickness are recommended as key indexes of the hot-rolled silicon steel strip. As the transverse thickness difference must be controlled below 7 μm, the corresponding , , should be controlled no more than 60, between -10∼10 μm and no more than 7.5 , respectively. Meanwhile, the requirement for the cross-sectional profile indexes is synchronous.

Screwdown load deviation threatens rolling mill safety and product quality. The contact between a 5 m rolling mill screwdown device and the back-up roll (BUR) bearing chock was simplified to a fixed hinge constraint, and the constraint of the keeper plates on the BUR bearing chock was simplified to a sliding hinge constraint. According to the BUR space force and moment equilibrium, a screwdown load deviation model affected by the BUR axial force was used to simulate the effect of the roll crossing degree on the screwdown load deviation. Screwdown load deviations were calculated for three rolling passes. The results are more consistent with the data than outputs calculated by a model that neglects axial force. Assumptions about the relationship between the load deviation and the work roll axial forces agree with the data. The results show that the BUR axial force causes a dynamic deviation of the screwdown load.