Application And Research Of Improved NSGA2 Optimization Algorithm In Steelmaking And Continuous Casting Scheduling Plan

As the representative industry with high-productivity,high-efficiency and advanced technology in the world,the steelmaking enterprises play a crucial role in national economic growth and social development.With the deepening of economic globalization and the rapid development of science and technology,the steel enterprises of China are facing growing competition from the world's market.The steelmaking and continuous casting make the key working procedure in steel enterprises,and the excellent scheduling plan of it can help enterprises to shorten the production period,improve productivity and increase profit.Therefore,it is of great practical significance to study the scheduling of steelmaking and continuous casting production.Based on the in-depth study of the goals and constraints involved in the steelmaking and continuous casting production scheduling process,an optimization model for scheduling planning is established,and the fast and elitist non dominated sorting genetic algorithm(NSGA2)is used to solve it.In order to solve the problem of how to select the optimal solution from the Pareto solution set obtained by the NSGA2,a deep research is carried out in this paper.First of all,the research results and current status of steelmaking and continuous casting scheduling plan are reviewed,and technology process and scheduling process of steelmaking and continuous casting production are deeply studied.On this basis,the scheduling constraints and objectives are abstracted according to the actual production requirements,and a multi-objective optimal scheduling model is established,whose optimization objectives includes minimum the total time that charges spend to wait for the equipment,minimum total interruption time for casting,minimum the deviations from ideal starting time of casting and minimum the time of conflict between the charges on the same equipment.Secondly,the proposed model is solved by NSGA2 which is one of the most classic multi-objective optimization algorithms.In order to solve the problem of how to select the optimal solution from Pareto solution set obtained by NSGA2,the priority strategy and the optimal solution decision method based on priority strategy is proposed.The simulation experiments of the model and NSGA2 are carried out based on the actual production data of the steel enterprises,the optimal solution is selected from the Pareto solution set by optimal solution decision method based on priority strategy.Different scale simulation experiments and comparative analysis prove that the optimal solution decision method proposed in this paper is superior to other optimal solution decision method,just like the fuzzy decision method,the best compromise solution strategy and the technique for order preference by similarity to an ideal solution(TOPSIS).Finally,in order to solve the existing problems of the algorithm,such as the solution speed is too slow,and the tine of obtaining the optimal solution is extended by introducing the optimal solution decision method,the priority strategy is applied to improve the internal of the algorithm,and an improved NSGA2 based on priority strategy is proposed.The improved algorithm and NSGA2 with optimal solution decision are respectively carried out simulation comparison experiments on different scales.The results show that the improved algorithm can solve the problem faster,and the performance of the improved algorithm is better under the premise of obtaining the optimal solution.