Neural network modeling of a plate hot-rolling process

Abstract The force, torque and slab temperature models of each pass in the plate hot-rolling process are established in this paper. In the first, an experimental model of a plate hot-rolling is represented. The structure of this model is in the neural network forms and predicts the steady-state values of force, torque and slab temperature. In the second part, the proposed dynamical models are compared with the classical empiric models commonly used in the rolling practice. The experimental data obtained from Eregli Iron and Steel Factory in Turkey was used for developing both of the models. Copyright © 2004 IFAC