The Optimal Scheduling of a Reversing Strip Mill: Studies Using Multipopulation Genetic Algorithms and Differential Evolution

Abstract

This article addresses a problem of minimizing the hot rolling time of an ingot, from a given initial thickness to a prescribed final one, subject to a number of system constraints. The idea is to determine the minimum possible odd number of passes, so that the ingot leaves in the same direction as it entered, which would ensure the necessary degree of reduction without violating the prescribed upper limits of the available torque and roll force. A maximum rolling velocity was also prescribed and additional restrictions were imposed on the rates of acceleration and deceleration inside the mill. The problem was solved by using a number of variants of genetic algorithms, including a multipopulation island model and differential evolution, besides the simple genetic algorithms. The results are compared with some earlier work based on a discrete dynamic programming technique, and a model based on an improved formulation is also presented.

Key Words:

• Genetic algorithms
• Differential evolution
• Island model of genetic algorithms
• Evolutionary computation
• Evolutionary optimization
• Discrete dynamic programming
• Optimization
• Rolling
• Hot strip mill
• Modeling
• Simulation
• Scheduling

Acknowledgments