Comparison of empirical and neural network hot-rolling process models

Abstract

Steel manufacturers are under pressure to improve their productivity levels by optimizing their process parameters to create maximum efficiency and quality levels. One of the keys to achieve this goal is the automation of the steel making process. Automation using artificial intelligence techniques applied to the hot rolling process is a potentially important steel manufacturing technique. The mathematical modelling of the process has been recognized as a desirable approach for designing mill equipment and ensuring productivity and service quality. However, such an analysis is generally very complex and time-consuming. Thus, there is considerable interest in developing simple and effective techniques to obtain accurate rolling force, torque, and slab temperatures. In this paper, a neural network (NN) is used to model the roughing stage of a plate hot rolling process. The NN approach can predict steady-state values of the force, torque, and slab temperature. The proposed NN model is compared with the classical empirical models commonly used in industrial practice. Experimental data obtained from the Ereğli Iron and Steel Factory in Turkey was used in developing the models.

An approximate method for computing the temperature distributions in roll and strip during rolling process

“…Serajzadeh et al 31 presented two-dimensional FEM model coupled with unsteady-state heat transfer equations with time-dependent boundary conditions to predict the work-roll temperature distributions during continuous hot slab rolling process. Recently, Oznergiz et al 32 used neural networks to obtain the temperature in hot rolling, but the method requires a lot of experimental data for training the network. An integrated thermo-mechanical model of thin slab direct rolling of Nb steel for hot rolling has been developed by Shahtout et al 33 The model makes use of a number of empirical relations available in literature.…”

Enhanced meta‐heuristic methods for industrial winding process modelling

“…The development of well-founded models to simulate the outputs of complex industrial processes is substantial enough to produce a good approximation of the output parameters. When compared to empirical methods that modelled the same process, model-based methods performed significantly better (Öznergiz et al, 2009;Sheta et al, 2009Sheta et al, , 2013. This expansion has shifted the focus of the intensification from control to modelling.…”