Design And Implementation About The Optimization Of The Rolling Schedules Based On Improved Genetic Algorithms

Setting-up calculation is the basic work of the continuous rolling operation and the most important problem of it is how to make the value of press load distribution of each step. The reasonable load distribution can make the control of modem rolling machine implement easily, consequently get a better control results. The study on load distribution has very important realistic meanings.As a new intelligent optimization algorithm, Genetic Algorithms has been used widely, and has excellent performance in solving complex questions, and it has been used in load distribution; Flatness and gauge are two important primary criteria in strip process, and recently they are at the front line of current study on strip rolling technology .In this paper, the capability of Genetic Algorithms is analyzed and researched, the Basic Genetic Algorithms is improved to increase the convergence speed and the precision of calculation, so the Improved Genetic Algorithms is presented. The results of simulations how that Improved Genetic Algorithms is better than the Basic Genetic Algorithms; The hot finishing steps are set as the study target, and study on load distribution and set-up calculation on the basis of conventional mathematic models with Improved Genetic Algorithms is carried out.Based on the rationality of traditional load distribution method, the Improved Genetic Algorithms is used. And the results optimized by Improved Genetic Algorithms are better than the experiential one's, the exit thickness, and crown are more feasible, It not only gives more press value to ensure playing equipment ability full in first several steps, but also fit the requirements of the precision of flatness and gauge of the last several steps.In this paper, the IGA applies to the rolling schedules. It is satisfied about the result. But it is not application to the spot. Because of the restriction of complexity and the craft conditions of the spot environment, whether the method introduces by this paper can be applied or not still need a further verification on the scene.