摘要
转炉炼钢过程中,配料直接影响钢水质量、冶炼效率及经济成本。传统配料方法依赖人工经验、缺乏科学依据。选择具备快速非支配排序机制、处理多目标优化问题有显著优势的第2代非支配排序多目标遗传算法(NSGA2)作为寻优算法,综合质量、吹损量、经济成本3个因素分别构建模型(成本、吹损为目标函数,质量作为约束条件)。针对算法初始种群分布不均匀、迭代后期局部搜索能力不强等问题,引入最大和最小拉丁超立方采样、自适应变异因子2种改进策略,提高了算法的寻优能力。通过历史数据检验,改进后的第2代非支配排序多目标遗传算法(INSGA2)能够在保证钢水质量的前提下搜寻更多的帕累托最优解,所选择的最佳配料方案预计可降低0.0122的吹损、节约经济成本36230元,为转炉配料提供高效、经济的指导。
In the process of converter steelmaking,the amount of ingredients directly affects the quality of molten steel,smelting efficiency and economic cost.Traditional batching methods rely on manual experience and lack scientific basis.The second generation non-dominated sorting multi-objective genetic algorithm(NSGA2)with fast non-dominated sorting mechanism and significant advantages in dealing with multi-objective optimization problems is selected as the optimization algorithm.The model is constructed by integrating three factors of quality,blow loss and economic cost(cost and blow loss are the objective functions,quality is the constraint condition).Aiming at the problems of uneven distribution of the initial population and weak local search ability in the later iteration of the algorithm,two improved strategies of maximum and minimum Latin hypercube sampling and adaptive mutation factor are introduced to improve the optimization ability of the algorithm.Through the test of historical data,the improved second generation non-dominated sorting multi-objective genetic algorithm(INSGA2)can search for more Pareto optimal solutions under the premise of ensuring the quality of molten steel.The selected optimal batching scheme is expected to reduce the blowing loss of 0.0122 and save the economic cost of 36230 yuan,providing efficient and economical guidance for converter batching.
作者
刘海
李爱莲
解韶峰
LIU Hai;LI Ailian;XIE Shaofeng(School of Automation and Electrical Engineering,Inner Mongolia University of Science and Technology,Baotou 014010,Nei Mongol,China;Key Laboratory of Process Industry Integrated Automation of Inner Mongolia Higher Education Institutions,Baotou 014010,Nei Mongol,China;Infrastructure Office,Inner Mongolia University of Science and Technology,Baotou 014010,Nei Mongol,China)
出处
《钢铁研究学报》
北大核心
2025年第9期1152-1161,共10页
Journal of Iron and Steel Research
基金
内蒙古自治区自然科学基金资助项目(2022MS06003)
支持地方高校改革发展基金资助项目(学科建设)。
关键词
NSGA2
转炉配料多目标优化
转炉吹损
钢水碳含量约束
钢水温度约束
钢水锰含量约束
NSGA2
multi-objective optimization of converter ingredient
converter blowing loss
carbon content constraint of molten steel
temperature constraint of molten steel
manganese content constraint in molten steel
