Analysis Of Shape Factors Of 6-high Cold Rolling Mill

Plate is an important material used in all areas of the national economy. With the increasing production and demand of cold-rolled strip in China in recent years, the departments have put forward higher requirements for the production of plate, especially in cold-rolled sheet.The strip is not only excellent in performance, but also has good plate flatness and precise geometric dimensions. As the research of shape control started late, coupled with the monopoly of foreign technology, the current domestic iron and steel enterprises to use most of the plate-shaped control system still need to be imported from abroad, so the shape control of cold-rolled products research has great prospects.The research object of this paper is a certain iron and steel group, cold rolling plant of 1200 mm cold rolling unit; the finite element model of the three-dimensional elastic deformation of the 6-high rolling mill was established by using the large-scale general finite element software ANSYS, the simulation of the six roller cold rolling mill rolling process. By a given different rolling process parameters for the simulation calculation and get the result,according to the result file to get the stress and strain in the process of rolling and rolling force distribution; Through the analysis of the strip after rolling, with the aid of APDL language programming to calculate the strip shape on the surface of the trend diagram, at the same time,relative length difference method is used to programming the flatness of strip after rolling the I index. Then based on the strip section and shape index, on the basis of the finite element model,the comparative analysis of the work roll bending force in the process of rolling, intermediate roll bending, intermediate roll speed across and width for the effect of strip shape; The influence relationship can be obtained accurately by the control panel, which provides the basis for obtaining the high quality plate.Finally, this paper also establishes the learning model of BP neural network in MATLAB,introduces the data obtained from the simulation experiment into the model, training and forecasting the sample data, and controls the error perfect model to realize the prediction of the plate index. Genetic algorithm is used to obtain the optimal BP neural network model, and the optimal condition parameters are obtained.