GA-IFM hybrid modeling for multi-pass cold rolling bending force preset

As industrial technology progresses, the quality requirements for cold-rolled steel strips, particularly dimensional accuracy and flatness, have become significantly stricter. A prediction model for the flatness of steel strips in the multi-pass rolling process of a six-high cold rolling mill is established based on the influence function method(IFM) in this paper. The model takes into account the influence of the bending forces on the width profile and flatness of the steel strip, and its accuracy is verified through industrial experiments. On this basis, the genetic algorithm(GA) is combined with the flatness prediction model to establish a preset model of work roll bending force to optimize the bending force settings in each pass. The research results indicate a progressive reduction in strip crown with increasing bending force, and the control efficiency coefficient of the crown by the bending force decreases successively from the first pass to the fifth pass. Through genetic algorithm optimization, the preset values of the work roll bending forces in each pass are obtained, providing valuable guidance for improving the flatness control of cold-rolled steel strips.