基于连续线性规划的多炼厂生产计划优化方法  

A petroleum multi-refinery production optimization method based on succes-sive linear programming

作　　者：董丰莲[1,2] 张丰胜 魏志伟 孙鑫 李月文[4] DONG Fenglian;ZHANG Fengsheng;WEI Zhiwei;SUN Xin;LI Yuewen(PetroChina Planning and Engineering Institute,Beijing 100086,China;CNPC Laboratory of Oil&Gas Business Chain Optimization,Beijing 100083,China;CNPC PetroChina Production&Business Management Department,Beijing 100007,China;Shanshu Technology(Beijing)Co.,Ltd.,Beijing 100102,China)

机构地区：[1]中国石油天然气股份有限公司规划总院,北京100086 [2]中国石油天然气集团有限公司油气业务链优化重点实验室,北京100083 [3]中国石油天然气集团有限公司生产经营管理部,北京100007 [4]杉数科技(北京)有限公司,北京100102

出　　处：《山东大学学报（理学版）》2024年第11期100-109,125,共11页Journal of Shandong University(Natural Science)

摘　　要：为了提升综合性石油公司盈利能力和解决带有整数变量和非凸双线性约束的多炼厂生产计划优化问题,本文通过对原油在多炼厂间的分配、各炼厂装置负荷以及产品方案进行整体优化,利用运筹学方法建立多炼厂生产计划优化模型。本文提出基于连续线性规划(successive linear programming,SLP)的混合整数非线性规划(mixed integer nonlinear programming,MINLP)求解方法,并提出一种基于业务特点的分支策略,使得求解过程能够快速收敛并且给出高质量的解。采用某石油企业的实际数据进行验证分析,结果表明所提出的算法在模型目标值和求解效率上均具有优势。To enhance the profitability of integrated oil companies and address the optimization problem of multi-refinery production planning with integer variables and non-convex bilinear constraints,we established an optimization model for multi-refinery production planning using operations research methods by holistically optimizing the allocation of crude oil among multiple refineries,the load of each refinery’s units,and the product slate.We proposed a solution method for mixed integer nonlinear programming(MINLP)based on successive linear programming(SLP)and introduced a branching strategy tailored to business characteristics,enabling the solution process to converge rapidly and provide high-quality solutions.Validation analysis using actual data from a petroleum enterprise demonstrated that the proposed algorithm offered advantages in both the model's objective value and solution efficiency.

关 键 词：多炼厂 生产计划 混合整数非线性规划 连续线性规划 分支策略 

分 类 号：O221.2[理学—运筹学与控制论] TE681[理学—数学]