Abstract:Using nonlinear elastic-plastic finite element method, a 3D FE simulation model of six-high CVC rolling process is developed with the nonlinear FE software MSC.Marc. In the model, the elastic deformation of rolls and the elastic-plastic deformation of workpiece were coupled as a whole. Based on the model, the changes of work roll bending force, intermediate roll bending, and intermediate roll transverse shifting were simulated. The effects of different rolling parameters, strip and rollers parameters on the strip flatness adjusting were investigated and the actuators’ corresponding flatness efficiency was obtained. The simulation results of the actuators efficiencies are served as the sample database of BP neural network which delivers high precision results of actuators efficiency to the automatic flatness control system. The problem that the finite element method is time consuming and difficult to be used to the online flatness control is solved, and the precision of flatness online control is enhanced by this method.
薛涛,杜凤山,孙静娜. 基于有限元与神经网络的板形调控功效[J]. 钢铁, 2012, 47(3): 56-60.
XUE Tao,DU Feng-shan,SUN Jing-na. Actuator Effectiveness Based on Finite Element and Neural Network. Iron and Steel, 2012, 47(3): 56-60.