双重目标绿色柔性车间调度的遗传算法研究

Research on genetic algorithm for dual-objective green flexible job shop scheduling

摘要

针对传统车间调度中能源消耗高、生产柔性不足的痛点,提出一种面向绿色制造的改进遗传算法(IGA).通过构建双目标优化模型实现最小化最大完工时间、最小化碳排放量的协同优化;设计双层编码机制(子作业序列层/处理机分配层)提升解空间表达能力;创新性融合动态交叉变异策略,使交叉率在0.6~0.8区间自适应调整、变异率在0.01~0.1区间动态优化;初期高位基因变异强化全局探索,后期低位基因微调促进局部收敛,实现分阶段基因操作.基于Brandimarte标准MK01数据集的实验表明:相较于标准遗传算法(GA)和NSGA-II,IGA在最大完工时间降低17.2%的同时,碳排放量减少16.8%.研究结果为绿色制造提供了兼具理论价值与工程应用潜力的调度决策工具.

Abstract

To address the challenges of high energy consumption and insufficient production flexibility in traditional workshop scheduling, this paper proposed an improved genetic algorithm (IGA) for green manufacturing. A dual-objective optimization model was constructed to jointly minimize the maximum makespan and carbon emissions. A dual-layer encoding mechanism (sub-job sequence layer/machine assignment layer) was designed to enhance solution space representation. A dynamic crossover and mutation strategy was integrated innovatively to enable adaptive crossover rate adjustment (0.6~0.8) and dynamic mutation rate optimization (0.01~0.1). High-order gene mutation strengthens global exploration in early stages, while low-order gene fine-tuning promotes local convergence in later stages, thus to achieve stage-based genetic operations. Experiments based on the Brandimarte benchmark MK01 dataset demonstrate that compared to standard genetic algorithm (GA) and NSGA-II, IGA reduces the makespan by 17.2% while cutting carbon emissions by 16.8%. The results of the research provide a scheduling decision tool with both theoretical value and engineering application potential for green manufacturing.

关键词

遗传算法 / 柔性车间调度 / 绿色制造 / 多目标优化 / 双层编码

Key words

genetic algorithm / flexible job shop scheduling / green manufacturing / multi-objective optimization / dual-layer encoding

参考文献

[1] 徐嘉琦, 田野. 基于改进遗传算法的柔性流水车间调度研究[J]. 制造技术与机床, 2024(4): 181-187.

[2] 刘冬冬, 方烁. 流水车间调度中的离散粒子群优化算法[J]. 阜阳师范大学学报(自然科学版), 2024, 41(2): 24-29.

[3] 孔文苑, 徐志杰, 汤斌. 两台机器下的流水车间调度算法与程序实现[J]. 电脑知识与技术, 2024, 20(18): 43-46.

[4] 邓海龙, 刘欢, 董芝萱, 等. 优化遗传算法求解柔性流水车间调度问题[J]. 电脑知识与技术, 2025, 21(2): 15-18.

[5] 辽宁省工业和信息化厅 关于印发《辽宁省绿色制造梯度培育及管理实施细则》的通知:辽工信资源〔2004〕119号[A/OL].(2024—08—26)[2025—04—20]. https://gxt.ln.gov.cn/gxt/tztg/2024090215372418778/index.shtml.

[6] XIAO Y J, ZHENG Y, YU Y T, et al. A branch and bound algorithm for a parallel machine scheduling problem in green manufacturing industry considering time cost and power consumption[J]. Journal of Cleaner Production, 2021, 320: 128867.

[7] GAGGERO M, PAOLUCCI M, RONCO R. Exact and heuristic solution approaches for energy—efficient identical parallel machine scheduling with time—of—use costs[J]. European Journal of Operational Research, 2023, 311(3): 845-866.

[8] 张福新, 白锋堂. 中长期煤炭消费碳排放与二氧化碳排放值预测[J]. 中国煤炭, 2022, 48(4): 36-40.

[9] YUAN M H, LI Y D, ZHANG L Z, et al. Research on intelligent workshop resource scheduling method based on improved NSGA—II algorithm[J]. Robotics and Computer—Integrated Manufacturing, 2021, 71: 102141.

[10] 赵雨山. 基于满意度的多目标柔性流水调度问题研究[D]. 大连: 大连理工大学, 2021: 36.

[11] 耿凯峰, 叶春明, 吴绍兴, 等. 分时电价下多目标绿色可重入混合流水车间调度[J]. 中国机械工程, 2020, 31(12): 1469-1480.