基于改进NSGA-Ⅲ的原油短期调度能耗优化  

Energy Consumption Optimization for Short-Term Scheduling of Crude Oil Operations Based on an Improved NSGA-Ⅲ

作　　者：侯艳[1] 牛聪 滕少华[1] 朱清华[1] HOU Yan;NIU Cong;TENG Shaohua;ZHU Qinghua(School of Computer Science and Technology,Guangdong University of Technology,Guangzhou 510006,China)

机构地区：[1]广东工业大学计算机学院,广东广州510006

出　　处：《工业工程》2024年第6期38-50,共13页Industrial Engineering Journal

基　　金：国家自然科学基金资助项目(61972102);广东省重点领域研发计划项目(2020B010166006)。

摘　　要：为了进一步提高原油短期调度问题的求解质量和优化效果,本文针对原油处理短期调度优化问题,提出一个两阶段优化求解策略。通过对供油罐到蒸馏塔的指派过程的分析,设计出能够成段保留父代基因的交叉算子和自适应改变变异概率的变异算子,提出NSGA-Ⅲ-ACMO算法求解原油短期调度问题。该算法在具有良好收敛性的同时又保证了种群的多样性,同时优化原油在管道的混合成本、罐底的混合成本、蒸馏塔的换罐成本、供油罐使用成本和能耗成本5个目标。针对能耗目标优化不彻底的问题,提出一个新的混合整数线性规划模型进一步优化能耗。该模型的优点是对于一个已知的详细调度,在不影响其他目标的情况下,可以将能耗目标优化到最小。实例分析表明,通过NSGA-Ⅲ-ACMO算法所得的调度与已有文献结果对比,单个目标优化效果提升9%~45%不等。在此基础上,使用本文提出的混合整数线性规划模型,能耗成本可以降低6.8%。从整体上看,本文所提算法在求解质量和优化效果上都表现出明显的优越性。In order to further improve the solution quality and optimization effectiveness of the short-term crude oil scheduling problem,a two-stage optimization strategy for addressing such problems is proposed.First,Through the analysis of the assignment process from charging tanks to distillers,a crossover operator that can preserve segmentally parent genes and a mutation operator that adaptively changes mutation probabilities are given.Additionally,the NSGA-Ⅲ-ACMO algorithm is introduced to solve the short-term crude oil scheduling problem,which ensures good convergence and population diversity while optimizing five objectives:crude oil mixing cost in pipeline and in charging tanks,tank-switching cost in distillers,tank usage cost,and energy consumption cost.To address the issue of incomplete optimization of energy consumption cost,a new mixed integer linear programming model is proposed for further optimization.The advantage of this model is that,for a given detailed schedule,it can minimize the energy consumption without affecting other objectives.A case study demonstrates that comparing the schedule obtained by the NSGA-Ⅲ-ACMO algorithm with the results of existing literature,the optimization of individual objectives is improved by 9% to 45%.On this basis,the proposed model can further reduce energy consumption cost by 6.8%.Overall,the NSGA-Ⅲ-ACMO shows the obvious superiority in both solution quality and optimization effectiveness.

关 键 词：原油短期调度 自适应算子 能耗优化 混合整数线性规划 

分 类 号：F406.2[经济管理—产业经济] TP301[自动化与计算机技术—计算机系统结构]