Optimisation of total roll power using genetic algorithms in a compact strip production plant

The application of optimisation techniques to hot rolling models can lead to the more efficient use of these models. In this work, a genetic algorithm has been used in order to design new hot rolling schedules with lower energy consumption through a reduction in the total roll power. Firstly, mean flow stress has been modelled for several Nb microalloyed steels produced in a compact strip production plant taking into account recrystallisation and precipitation models. The selected mean flow stress model has been validated against the values obtained from the industrial hot rolling forces using the Sims approach. Secondly, the model has been integrated with a genetic optimisation algorithm and new reductions have been proposed in order to decrease the total rolling power, maintaining all the requirements. The reductions achieved can be up to 10%.