Collaborative Modeling And Optimization For Hot Rolling Scheduling Based On Multi-objective Evolutionary Algorithm

Iron and steel industry is the pillar industry of the national economy,but also industrial energy consumption.Hot rolling is one of the most important processes in iron and steel production.Improving the scheduling level of hot rolling process is of great significance to enterprises.Although the existing literature has completed the research on the production scheduling of the sub-processes of hot rolling,such as heating furnace scheduling and rolling planning,there is still room for improvement in the aspects of heating furnace scheduling and rolling planning,modeling and optimization of hot rolling production and energy coordination.In this paper,the collaborative modeling and optimization method of hot rolling scheduling based on multi-objective evolutionary algorithm is studied.The specific research work is as follows:In order to solve the problem of synergistic scheduling of heating furnace and rolling schedule in hot rolling process,the total heating time of slab and the total penalty value between slab are considered.an integrated mathematical model is established according to the requirements of production process and rolling schedule.An improved multi-objective evolutionary algorithm is proposed,which accelerates Pareto frontier search and finds feasible regions by adding constraints step by step in multiple stages.The experimental results show that the proposed method has obvious advantages over other modeling and optimization methods,and can provide a reference for the actual scheduling of hot rolling process.Aiming at the problem of cooperation between hot rolling process and energy production and consumption process,an energy side balance model was established.Taking hot rolling scheduling model and energy balance model as upper and lower layers,an interactive solution strategy based on alternating direction multiplier framework is proposed.The energy consumption of hot rolling process is regarded as transplantable load and combined with other schedulable variables to carry out alternate iteration.Through daytime and daytime optimization,the optimal solution is obtained to meet the actual demand of both production and energy.Experimental results show that the proposed method can achieve a good balance between production cost and energy cost,which is helpful to improve production efficiency and reduce energy emissions.