基于“炉-机对应”的炼钢-连铸生产调度问题遗传优化模型  

Genetic optimization model of steelmaking-continuous casting production scheduling based on the “furnace-caster coordinating” strategy

作　　者：刘倩 杨建平 王柏琳[2,3] 刘青 高山[4] 李宏辉 LIU Qian;YANG Jian-ping;WANG Bai-lin;LIU Qing;GAO Shan;LI Hong-hui(State Key Laboratory of Advanced Metallurgy,University of Science and Technology Beijing,Beijing 100083,China;Donlinks School of Economics and Management,University of Science and Technology Beijing,Beijing 100083,China;Engineering Research Center of MES Technology for Iron and Steel Production,Ministry of Education,Beijing 100083,China;Laiwu Iron and Steel Group Yinshan Section Steel Co.Ltd.,Laiwu 271104,China)

机构地区：[1]北京科技大学钢铁冶金新技术国家重点实验室,北京100083 [2]北京科技大学东凌经济管理学院,北京100083 [3]钢铁生产制造执行系统技术教育部工程研究中心,北京100083 [4]莱芜钢铁集团银山型钢有限公司,莱芜271104

出　　处：《工程科学学报》2020年第5期645-653,共9页Chinese Journal of Engineering

基　　金：教育部博士学科点专项科研基金资助项目(20090006110024);中央高校基本科研业务费专项基金资助项目(FRF-BR-17-029A)。

摘　　要：针对炼钢-连铸过程因车间布局复杂造成工序间钢水交叉供应频繁、等待时间过长以及天车调度困难等问题,本文建立以计划内所有炉次总等待时间最小为优化目标的炼钢-连铸过程生产调度模型,并采用改进的遗传算法求解该模型.在遗传操作过程中,引入"炉-机对应"调控策略以改善初始种群质量,并根据转炉(精炼)与连铸作业周期的比较,来确定是否对个体进行交叉、变异操作.以国内某中大型炼钢厂主要生产模式下的实际生产计划为仿真算例进行实验,结果表明:本文提出的基于"炉-机对应"的改进遗传算法的性能显著优于基本遗传算法及启发式算法,针对炼钢厂产量占比超过80%的主要生产模式4BOF-3CCM下的算例1,优化了生产过程等待时间,工序间最长等待时间由77 min减小到54 min;炉-机匹配程度也明显提高,3号精炼炉去往3号连铸机的钢水比例由25%提升到67%,减少了个别炉次由于设备随机指派造成的工序设备间对应关系不明确及由于生产路径不合理造成等待时间过长的现象,为研究炼钢厂复杂生产调度问题提供了一种高效的解决方案.To avoid the frequent cross supply, excessive waiting time and difficult crane dispatching of molten steel among processes that resulted from the complex workshop layout of the steelmaking continuous casting process, a production scheduling model for the steelmaking-continuous casting process was established in this study with the objective of optimizing and minimizing the total waiting time of all furnaces in the plan. Moreover, an improved genetic algorithm was used to solve the model. In the operation process of the genetic algorithm, the "furnace-caster coordinating" strategy was introduced to improve the quality of the initial population. Furthermore, the crossover and mutation operations were determined based on the comparison of the operating cycles of steelmaking (refining) and continuous casting. The actual production plan under the main production mode of a large domestic steel plant was utilized as the simulation sample. Results show that the performance of the improved algorithm based on the " furnace-caster coordinating" strategy is significantly better than that of the basic genetic and heuristic algorithms. The output of Sample 1 of the main production model 4 BOF-3 CCM accounts for more than 80% in steel plants. After optimization, the waiting time of the production process is optimized, and the maximum waiting time between steelmaking and continuous casting processes is reduced from 77 to54 min. The degree of matching of the refining furnace-continuous caster machine is significantly improved. Moreover, the proportion of molten steel poured from the No. 3 refining furnace on the No. 3 continuous caster machine is increased from 25% to 67%. The phenomenon of unclear matching among processes and facilities caused by random facility assignment for one or two furnaces is reduced. Furthermore, the phenomenon of excessive waiting time caused by unreasonable production path for one or two furnaces is reduced. An efficient solution for the study of complex production scheduling problems in steel plants i

关 键 词：炼钢-连铸 生产调度 改进遗传算法 炉-机对应 生产模式 

分 类 号：TF087[冶金工程—冶金物理化学]