Under the background of intelligent manufacturing and Industry 4.0, the traditional flexible job-shop scheduling problem is often constrained by inadequate resource allocation due to the neglect of human factors. To address this issue, a multi-objective optimization model was developed by integrating worker learning effects and fatigue mechanisms, aiming to minimize the makespan, total energy consumption, and labor cost. An improved multi-objective salp swarm algorithm was proposed to solve the problem efficiently. The algorithm incorporated a Circle chaotic initialization mechanism to enhance population diversity. A differential evolution strategy was employed to strengthen local search, and a virtual force-based chain-following mechanism was designed to balance global exploration and local exploitation. The effectiveness of the proposed method was validated on extended benchmark instances using inverted generational distance and hypervolume as evaluation metrics. A real-world automotive wiring harness scheduling case was further analyzed. Experimental results show that the obtained Pareto solutions are closer to the origin and more uniformly distributed. The result offers a novel modeling framework and an effective solution approach for workshop scheduling problems that consider human-related characteristics, contributing theoretical significance to the field.
上述研究详细描述了考虑工人作为生产约束条件的双资源约束的调度模型,并且在工人因素关注中进行多方面的考虑。然而在实际生产过程中,工人的因素会受到技能熟练度、疲劳程度、工人技能等级等因素影响。因此,现提出考虑工人学习效应的调度模型,搭建以最小化最大完工时间、最小化总能耗、最小化人工成本为目标的问题模型,为求解该问题,设计改进多目标樽海鞘群算法,通过引入 Circle 混沌映射,提高种群多样性,避免陷入初始局部最优,引入差分演化机制增强种群的局部搜
考虑工人学习效应的 DRCFJSP 问题是考虑工人在实际完成工序过程中,其经验值逐步提升,从而使后续加工效率提高,表现为单位加工时间随经验增长而逐步下降,并且不同的工人技能等级存在差异,初始经验值和学习率有所不同。此外,结合实际工业场景,为避免长期连续作业带来的效率下降,还引入疲劳机制,模拟工人因工作负荷累积而导致的效率波动。考虑工人学习效应的 DRCFJSP 可描述为:车间中共有 n 个工件,配置有 m 台可选机器和 w 名工人,任意工件j都有确定的 i 道工序组成,每道工序需分配一台机器与一名工人共同完成。需要确定的问题:确定所有工序的加工顺序,分配机器与工人,以获得最佳的调度方案。假设条件如下。
随机生成或规则化初始化易导致解空间探索不均,陷入局部最优陷阱,并且由于工序排序、资源分配等多维度决策变量间存在强关联,独立初始化破坏解的结构合理性。针对上述问题,本文采用改进 Circle 混沌映射[20]建立三维协同初始化序列机制,对 OS、WS、MS 采用独立混沌序列,避免维度间干扰;通过工序索引隐式维系变量间的逻辑关联,并且通过混沌值的分布特性自动适应不同规模的调度问题。混沌映射函数为
(1)针对传统柔性作业车间调度问题中忽视人因因素的问题,提出了一种融合工人学习效应与疲劳机制的双资源约束柔性作业车间调度模型。该模型综合考虑了工人技能等级、学习速率差异、疲劳阈值等多个现实因素,能够更真实地刻画生产过程中工人效率随经验与疲劳动态变化的规律。在模型求解方面,设计并实现了改进多目标樽海鞘群算法(IMSSA),该算法通过引入 Circle 混沌初始化、差分进化机制以及虚拟力与链式跟随策略,显著提升了解的多样性与算法的收敛性能。
ZhangGuohui, CaiYihao, LiZhixiao, et al. Research on flexible job shop sched-uling problem considering limited AGV tra-nsportation resources[J]. China Mechanical Engineering, 2025, 36(8): 1811-1823.
ChenZhiye, HuYi, LiuJun, et al. Improved genetic algorithm based on reinforcement learning for flexible job shop scheduling problem[J]. Science Technology and Engineering, 2024, 24(25): 10848-10856.
[7]
ZhangH, ChenY, ZhangY, et al. Energy-saving distributed flexible job shop scheduling optimization with dual resource constraints based on integrated Q-learning multi-objective greywolf optimizer[J]. CMES-Computer Modeling in Engineering & Sciences, 2024, 140(8): 1459-1483.
Vital-SotoA, BakiM F, AzabA. A multi-objective mathematical model and evolutionary algorithm for the dual-resource flexible job-shop scheduling problem with sequencing flexibility[J]. Flexible Services and Manufacturing, 2023, 35: 626-668.
ZhangWeicun, GuHongyu. Job-shop scheduling problems considering similar learning effect in one-worker and multiple-machine patterns[J]. China Mechanical Engineering, 2023, 34(14): 1701-1709.
XiaoJiasheng, ChangDaofang, QianZhenhua, et al. Image segmentation based on self-adaptive fruit fly algorithm optimizing fuzzy means clustering algorithm[J/OL]. Control Engineering of China (2024-05-09) [2025-06-28]. https://doi.org/10.14107/j.cnki.kzgc.20240045.
[21]
ZhaoC, FangJ, ChengT, et al. A note on the time complexity of machine scheduling with DeJong's learning effect[J]. Computers & Industrial Engineering, 2017, 112: 447-449.
CaoLei, YeChunming, HuangXia. Multi-objective flexible job-shop scheduling based on learning effects[J]. Computer Integrat-ed Manufacturing Systems, 2018, 24(8): 2023-2034.
[24]
XuS, HallN G. Fatigue, personnel scheduling and operations: Review and research opportunities[J]. European Journal of Operational Research, 2021, 295(3): 807-822.
[25]
TanmayH, BijoyK D. Analysis of decision policies for two-echelon sustainable supply chain inventory model with learning and forgetting[J]. Computers & Industrial Engineering, 2025, 209: 111409.
[26]
PenaI, ChenH. Exploring team dynamics and performance in extended space missions using agent-based modeling[J]. Plos One, 2025, 20(10): e0332496.
[27]
MirjaliliS, GandomiA H, MirjaliliS Z, et al. Salp swarm algorithm: a bio-inspired optimizer for engineering design problems[J]. Advances in Engineering Software, 2017, 114: 163-191.
[28]
XueZ, YuJ, ZhaoA, et al. Optimal chiller loading by improved sparrow search algorithm for saving energy consumption[J]. Journal of Building Engineering, 2023, 67: 105980.
[29]
AkramK, BhuttaM U, ButtS I, et al. A Pareto-optimality based black widow spider algorithm for energy efficient flexible job shop scheduling problem considering new job insertion[J]. Applied Soft Computing, 2024, 164: 111937.
[30]
LuoQ, DengQ, GongG, et al. An efficient memetic algorithm for distributed flexible job shop scheduling problem with transfers[J]. Expert Systems with Applications, 2020, 160: 113721.
[31]
ZhangH, QinC, XuG, et al. An energy-saving distributed flexible job shop scheduling with machine breakdowns[J]. Applied Soft Computing, 2024, 167: 112276.
[32]
ZandevakiliH, RashediE, MahaniA. Gravitational search algorithm with both attractive and repulsive forces[J]. Soft Computing, 2019, 23: 783-825.
[33]
WeiL S, LiE C. A grey prediction-based reproduction strategy for many-objective evolutionary algorithm[J]. International Journal of Intelligent Systems, 2024(1): 8994938.
[34]
MaoH, WangC, HeY, et al. Advancing SWAT model calibration: a U-NSGA-Ⅱ-based framework for multi-objective optimization[J]. Water, 2024, 16(21): 3030.
WangYufang, GeShiyu, ChenFan, et al. Dual resource constrained flexible job-shop green scheduling considering learning effect[J/OL]. Control Engineering of China (2024-12-27) [2025-05-26]. https://doi.org/10.14107/j.cnki.kzgc.20240778.