基于改进GEP的绿色柔性作业车间调度研究  

Research on Green Flexible Job Shop Scheduling Based on Improved Gene Expression Programming Algorithm

作　　者：王婷[1] 于颖 赵曜 Wang Ting;YU Ying;ZHAO Yao(School of Management,Guizhou University,Guiyang 550025,China;Engineering Training Center,Guizhou Institute of Technology,Guiyang 550001,China)

机构地区：[1]贵州大学管理学院,贵阳550025 [2]贵州理工学院工程训练中心,贵阳550001

出　　处：《组合机床与自动化加工技术》2025年第3期219-225,231,共8页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：贵州省科学技术基金项目(黔科合基-ZK[2021]一般275)。

摘　　要：降低制造过程能源消耗和碳排放是近年来备受制造业关注的问题,车间生产是制造过程产生能耗的主要因素之一,合理的车间调度方法可以有效降低车间生产能耗和碳排放。针对绿色柔性作业车间调度问题(green flexible job shop scheduling problem,GFJSP),提出了一种改进的多目标基因表达式编程(multi-objective gene expression programming,MOGEP)算法,并建立起以最大完工时间和总能耗为优化目标的数学模型。针对GFJSP的特点和MOGEP算法的求解方式,设计了用于车间调度问题的个体评价机制;针对算法特殊的基因构造形式,设计了基于K-表达式的变异操作和重组操作;提出了基于个体的自适应遗传算子,能够动态地调整遗传操作的概率;在MOGEP框架中融入了具有5层邻域结构的禁忌搜索策略,避免算法过早陷入局部最优。通过仿真对比实验证明,改进MOGEP算法在兼顾解的分布性的同时增强了全局收敛能力,具有更高的探索效率;且其生成的调度规则能够有效优化完工时间和生产能耗,具有实际应用价值。Reducing energy consumption and carbon emissions in the manufacturing process has been a major concern for the manufacturing industry in recent years.Workshop production is one of the main factors contributing to energy consumption in the manufacturing process,and a reasonable workshop scheduling method can effectively reduce energy consumption and carbon emissions in workshop production.An improved multi-objective gene expression programming(MOGEP)algorithm is proposed for the green flexible job shop scheduling problem(GFJSP),and a mathematical model is established with the optimization objectives of maximizing the completion time and total energy consumption.Based on the characteristics of GFJSP and the solution method of MOGEP algorithm,an individual evaluation mechanism for the job shop scheduling problem is designed.In view of the special gene structure of the algorithm,we designed mutation and recombination operations based on K-expressions.Proposed an individual-based adaptive genetic operator that can dynamically adjust the probability of genetic operations.A tabu search strategy with a 5-layer neighborhood structure is integrated into the MOGEP framework to avoid the algorithm from falling into local optima prematurely.The simulation comparison experiments prove that the improved MOGEP algorithm enhances the global convergence ability while taking into account the distribution of solutions,and has higher exploration efficiency.The scheduling rules generated by it can effectively optimize the completion time and production energy consumption,and have practical application value.

关 键 词：绿色柔性作业车间调度 多目标基因表达式编程 个体评价机制 自适应遗传算子 禁忌搜索策略 

分 类 号：TH165[机械工程—机械制造及自动化] TG659[金属学及工艺—金属切削加工及机床]