The setting of rolling schedule in tandem cold mill is one of the most crucial contents in rolling process, which will have a direct impact on product quality and production e ciency. According to the actual requirements in the rolling process, a multiobjective function based on in uence function method was built. The objective function was aimed specially at thin gauge strip and solved by Tabu search algorithm. Meanwhile, in order to avoid strip slipping by the reduction of friction coe cient, the tension schedule was corrected according to the rolling length of work roll. The proposed optimization method was successfully applied to a 1450-mm 5-stand tandem cold mill. Application results show that the optimized rolling schedules are more close to the actual requirements and the atness quality is improved greatly.

In cold strip rolling control system, rolling force and forward slip are the prerequisites for the model setting calculation, and the deformation resistance and friction coefficient are the main parameters that affect their predictions. A new method based on objective function is first proposed in this paper to improve the calculation accuracy of rolling force and forward slip, and the deformation resistance and friction coefficient are taken as optimisation variables. Using the multi-population co-evolutionary algorithm to solve the objective function, the required rolling force and forward slip are obtained. The pre-set values of rolling force and roller line speed are compared with the actual measured ones in a 1450 mm five-stand tandem cold mill and other researcher's method. Results show that the calculated values are in fair agreements with the on-line measured ones, and the thickness and flatness accuracy of the final product are improved.

Purpose In the process of cold rolled strip, there is tight coupling between flatness control and gauge control. The variation of the roll gap caused by the change of bending force will lead to the change of rolling force. Furthermore, it can cause a deep impact on the control accuracy of strip exit thickness and exit crown. The purpose of this paper is to improve the accuracy of the bending force preset value for cold rolled strip. Design/methodology/approach In this paper, the bending force preset control strategy with considering of rolling force was proposed for the first time and the preset objective function of bending force was established on the basis of the two-objective optimization of bending force and rolling force. Meanwhile, the multi-objective intelligent algorithm – INSGA-II – was used to solve the objective function. Findings The proposed bending force multi-objective preset model has been tested in a 1,450 mm tandem cold rolling line. The analyzed results of field data show that the deviations of strip exit thickness and exit crown are reduced effectively by using the improved model, and at the same time, more reasonable bending force preset values are obtained, which can enhance the accuracy of flatness preset control. Originality/value A preset model of bending force with considering flatness and gauge is proposed in this paper and the multi-objective function of bending force preset is established on the basis of the two-objective optimization of bending force and rolling force. The value lies in proposing a new decoupling method of rolling force and bending force.

Under the background of industry 4.0, advanced strip control process is a central part of rolling intelligent manufacturing. In the mainstream rolling control process, the work roll bending and the intermediate roll bending are turned on at the same time. Both stepwise methods and alternative methods are conducted by sacrificing adjustment ability. In this paper, the dimension of influencing factors is increased by considering adjustment direction as constraint operator. In the rolling control process, a new intelligent assignation strategy of collaborative optimization based on artificial neural networks and Topkis-Veinott has been proposed. In AINTV collaborative optimization, the thought patterns of searching and the thought patterns of learning are combined. Five field test experiments are conducted and the flatness in different rolling stages and in different strip area is analyzed. Keywords Rolling control process Á Artificial neural networks Á Intelligent manufacturing Á Collaborative optimization Á Calculation of bending force

No abstract