Rolling Mill Force Control by a Neural Network

FRANCISCO ROSSOMANDO; JOSE DENTI FILHO

Belo Horizonte, Brasil

Congreso; 60º Anual Congress da ABM; 2005

Asociaçao Brasileira de Metalurgia

In this paper, identification and control in the rolling mill process provide real application of non linear neural control. Different control structures based on neural model of the simulated plant are proposed. The results of the neural model are tested and compared, to obtain a solution of the force control problem to obtain a better strip crown. Knowing the advantage of the non linear modeling technique, all neural approaches increase the control precision.