Machine learning concepts, such as the support vector machine (SVM), have been theoretically discussed in great detail, but in industrial applications still rather old-fashioned solutions are preferred. To show that learning concepts improve industrial planning, scheduling, and steering processes, a cooperation with a steel manufacturer was initiated to build a prototype pass schedule calculato...

This contribution deals with the modeling and control of flatness defects in form of so–called ski–ends which occur during the hot rolling process of heavy plates. These ski–ends are caused by asymmetrical rolling conditions, e.g., different work roll circumferential speeds or vertical temperature gradients. In a first step, a physics–based model for asymmetrical rolling is derived based on the...

Pearlitic steels present very interesting mechanical properties when weldability requirements are not too severe. Thin gauge pearlitic steels require at least one intermediate annealing treatment between hot rolling and cold rolling. The globularised cementite in medium carbon steels provides then higher ductility, formability and machinability. On the other hand, in-line induction heating devi...

Rolling processes for which the characteristic length scale reaches into the range where size effects become important are receiving increased interest. In particularly, this is owed to the roll-molding process under development for high-throughput of micronscale surface features. The study presented revolves around the rolling induced effect of visco-plasticity (ranging hot and cold rolling) i...

In this case study we discuss a simple control system used for obtaining a desirable downstream surface temperature inside a hot rolling steel sheet, presented by Bao Steel in the HK Study Group with Industry, held at the City University of Hong Kong, July 2002.