doi:10.3969/j.issn.1007-7375.2023.03.014基于改进SPEA2的原油短期调度问题研究王书娟，侯艳，滕少华，朱清华(广东工业大学计算机学院，广东广州510006)摘要:针对原油短期调度多目标优化问题，在分析已有多目标模型对原油调度过程中的供油罐个数、供油罐切换次数、原油在管道中的混合成本和供油罐罐底混合成本这4个目标优化的基础上，本文建立的模型增加了原油在管道转运过程中的能耗成本这一优化目标，使模型更吻合生产实际。在SPEA2算法中引入极值归档集，结合MOGWO算法指导极值归档集更新来提高算法的全局搜索能力；利用余弦相似度对归档集进行裁剪操作，以保证归档集中个体的多样性。将改进算法与多个具有代表性的进化多目标优化算法进行对比实验，结果表明，本文所提出算法在求解原油短期调度问题时性能较优。关键词:原油调度；多目标优化；SPEA2算法；极值归档集中图分类号:TP301文献标志码:A文章编号:1007-7375(2023)03-0124-10ResearchonShort-termCrudeOilScheduleBasedonImprovedSPEA2WANGShujuan,HOUYan,TENGShaohua,ZHUQinghua(SchoolofComputers,GuangdongUniversityofTechnology,Guangzhou510006,China)Abstract:Tosolvethemulti-objectiveoptimizationproblemofshort-termcrudeoilscheduling,onthebasisoffourobjectivesinexistingoptimizationmodelsincludingthenumberofchargingtanks,thetimesofchargingtankswitching,themixingcostofcrudeoilinpipelinesandthemixingcostofchargingtankbottomsinacrudeoilschedulingprocess,themodelestablishedinthispaperaddsanoptimizationobjectiveoftheenergyconsumptioncostofcrudeoiltransferringthroughpipelines,whichismorecoincidenttorealproduction.TheextremevaluearchivesetisintroducedintoStrengthParetoEvolutionaryAlgorithm2(SPEA2),whileMulti-ObjectiveGreyWolfOptimizer(MOGWO)algorithmiscombinedtoguidetheupdateoftheextremevaluearchivesettoenhancetheglobalsearchabilityofthealgorithm;thecosinesimilarityisadoptedtoprunetheextremevaluearchivesettoimprovethediversityofindividualsintheset.Themodifiedalgorithmiscomparedwithseveralrepresentativeevolutionarymulti-objectiveoptimizationalgorithms,andtheexperimentalresultsshowthattheproposedonehasbetterperformanceinsolvingtheshort-termschedulingproblemofcrudeoil.Keywords:crudeoilschedul...
