目的 针对包装行业智能生产车间调度多采用静态指标优化,面对设备突发故障时生产效率低、调度稳定性差的问题,建立兼顾生产效率与调度稳定性的多目标优化模型。方法 以设备突发故障为典型动态扰动事件,构建最小化最大完工时间、最小化重调度扰动的多目标混合整数规划模型;提出一种遗传算法-变邻域搜索（GA-VNS）混合算法,采用双链编码遗传算法实现全局搜索,设计三类面向故障重调度的定制化邻域结构完成局部深度优化,通过故障状态投影、种群可行化修复与解回馈机制实现二者协同。结果 仿真算例表明,面对设备突发故障场景,该混合算法可有效规避局部最优解;在小规模包装车间算例中,较传统遗传算法最优完工时间缩短2 min;与NSGA-Ⅱ、PSO、禁忌搜索等算法相比,在完工时间与调度扰动两项指标上均表现更优且求解性能稳定。结论 GA-VNS混合算法在最优解质量与重调度稳定性方面均优于单一启发式算法,可为包装行业智能车间设备故障下的动态调度提供技术支撑。
Abstract
The work aims to establish a multi-objective optimization model balancing production efficiency and scheduling stability to deal with the problems that scheduling in intelligent production workshops of the packaging industry mostly adopts static indicator optimization, and suffers from low production efficiency and poor scheduling stability when facing unexpected equipment failures. Taking an unexpected equipment failure as a typical dynamic disturbance event, a multi-objective mixed-integer programming model was constructed to minimize the maximum makespan and minimize rescheduling disturbance. A hybrid genetic algorithm-variable neighborhood search (GA-VNS) algorithm was proposed. The algorithm implemented global search via a genetic algorithm with double-chain encoding, designed three types of customized neighborhood structures for failure-oriented rescheduling to achieve in-depth local optimization, and realized the collaboration between the two modules through failure-state projection, population feasibility repair and solution feedback mechanisms. Simulation cases showed that the hybrid algorithm could effectively avoid local optima under unexpected equipment failure scenarios. In the small-scale packaging workshop instance, the optimal makespan was reduced by 2 min compared with the traditional genetic algorithm. Compared with algorithms including NSGA-Ⅱ, PSO and Tabu Search, it performed better on both makespan and scheduling disturbance indicators with stable solving performance. The GA-VNS hybrid algorithm outperforms single heuristic algorithms in both optimal solution quality and rescheduling stability, and can provide technical support for dynamic scheduling of intelligent workshops in the packaging industry under equipment failures.
关键词
包装智能车间 /
动态调度 /
遗传算法 /
变邻域搜索 /
多目标优化
Key words
intelligent packaging workshop /
dynamic scheduling /
genetic algorithm (GA) /
variable neighborhood search (VNS) /
multi-objective optimization
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 田雪颖, 商乾, 管清华. 智能制造及数字化转型工业4.0时代的企业革新之路[J]. 军民两用技术与产品, 2024(12): 8-13.
TIAN X Y, SHANG Q, GUAN Q H.The Innovation of Enterprises' Intelligent Manufacturing and Digital Trasformation in the Era of Industry 4.0[J]. Dual Use Technologies & Products, 2024(12): 8-13.
[2] 窦水海, 于超宇, 白慧娟, 等. 基于改进NSGA-III算法的智能生产车间多AGV任务分配问题研究[J]. 包装工程. 2026, 47(3): 119-132.
DOU S H, YU C Y, BAI H J, et al.Multi-AGV Task Allocation in Intelligent Production Workshops Based on an Improved NSGA-III Algorithm[J]. Packaging Engineering. 2026, 47(3): 119-132.
[3] WANG L, LI R, CHEN J F.A Swarm Intelligence Pptimization Algorithm for Human-Robot Collaborative Energy-Efficient Shop Scheduling[J]. SCIENTIA SINICA Technologica, 2024, 54(9): 1676-1692.
[4] ZHANG J J, LU ZH P, DING J W, et al.An Effective Local Search Algorithm for Flexible Job Shop Scheduling in Intelligent Manufacturing Systems[J]. Engineering. 2025, 50, 117-127.
[5] 卫诚琨, 周俊. 订单驱动下基于强化学习的智能车间AGV调度[J]. 上海工程技术大学学报, 2023, 37(4): 397-403.
WEI C K, ZHOU J.AGV Scheduling for Order-Driven Intelligent Workshop Based on Reinforcement Learning[J]. Journal of Shanghai University of Engineering Science, 2023, 37(4): 397-403.
[6] 孙磊, 屠佳佳, 毛慧敏, 等. 针织智能车间自动换筒任务调度技术[J]. 纺织学报, 2023, 44(12): 189-196.
SUN L, TU J J, MAO H M, et al.Task Scheduling Technology for Automatic Bobbin Replacement in Intelligent Knitting Workshop[J]. Journal of Textile Research, 2023, 44(12): 189-196.
[7] LI R, GONG W, LU C.A Reinforcement Learning Based RMOEA/D for Bi-Objective Fuzzy Flexible Job Shop Scheduling[J]. Expert Systems with Applications, 2022, 203: 117380.
[8] DUAN J, LIU F, ZHANG Q, et al.Genetic Programming Hyper-Heuristic-Based Solution for Dynamic Energy-Efficient Scheduling of Hybrid Flow Shop Scheduling with Machine Breakdowns and Random Job Arrivals[J]. Expert Systems with Applications, 2024, 254: 124375.
[9] TAO X R, PAN Q K, GAO L.An Efficient Self-Adaptive Artificial Bee Colony Algorithm for the Distributed Resource-Constrained Hybrid Flow Shop Problem[J]. Computers & IndustrialEngineering, 2022, 169: 108200.
[10] 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.
XU J Q, TIAN Y.Improved Genetic Algorithm for Flexible Flow Shop Scheduling[J]. Manufacturing Technology & Machine Tool, 2024, (4): 181-187.
[11] 李瑞, 徐华, 杨金峰, 等. 改进近邻人工蜂群算法求解柔性作业车间调度问题[J]. 计算机应用研究, 2024, 41(2): 438-443.
LI R, XU H, YANG J F, et al.Improved Algorithm of Near-Neighbor Artificial Bee Colony for Flexible Job-Shop Scheduling[J]. Application Research of Computers, 2024, 41(2): 438-443.
[12] WANG J, ZHENG H, ZHAO S, et al.Energy-Aware Remanufacturing Process Planning and Scheduling Problem Using Reinforcement Learning-Based Particle Swarm Optimization Algorithm[J]. Journal of Cleaner Production, 2024, 476: 143771.
PDF(685 KB)
渝公网安备 50010702501716号 渝ICP备15012534号-2
