锻压技术

柔性车间冲压与物流资源多维度联合遗传调度

英文标题：Multi-dimensional joint genetic scheduling of stamping and logistics resources in flexible workshops

作者：李江涛1 2

单位：（1.濮阳职业技术学院数学与信息工程学院河南濮阳 457000 2.河南大学濮阳工学院河南濮阳 457000）

分类号：TP301.6

出版年,卷(期):页码：2024,49(9):254-260

摘要：

为了提高柔性冲压车间的生产效率，实现多维度资源的合理调度，提出了基于小生境引导遗传算法的联合调度方法。分析了柔性冲压车间中生产和物流的耦合过程，建立了带约束的多维度资源联合调度优化模型。将遗传算法染色体区分为先验体和搜索体，将先验体适应度作为先验信息引导搜索体的搜索方向，进而提出了小生境引导遗传算法并将其应用于调度问题求解。经校企合作单位的柔性冲压车间生产验证，小生境引导遗传算法得到的调度方案的完工时间最短（57.6 h），比标准遗传算法减少了10.4%，比遗传-郊狼混合算法减少了5.6%，比自适应差分进化算法减小了4.6%。实验结果表明，所提方法在多维度资源联合调度中具有优越性。

In order to improve the production efficiency of flexible stamping workshops and achieve reasonable scheduling of multi-dimensional resources, a joint scheduling method based on niche guided genetic algorithm was proposed. Then, the coupling process between production and logistics in a flexible stamping workshop was analyzed, and a multi-dimensional resource joint scheduling optimization model with constraint condition was established. Furthermore, the genetic algorithm chromosomes was divided into prior bodies and search bodies, and the prior body fitness was used as the prior information to guide the search direction of the search body. A niche guided genetic algorithm was proposed and applied to solve the scheduling problems. The production verification in the flexible stamping workshop of school enterprise cooperation units shows that the completion time of scheduling scheme obtained by the niche guided genetic algorithm is the shortest (57.6 h), which is 10.4% less than that of the standard genetic algorithm, 5.6% less than that of the genetic coyote hybrid algorithm, and 4.6% less than that of the adaptive differential evolution algorithm. Thus, the experimental results show that the proposed method has superiority in the multi-dimensional resource joint scheduling.

基金项目：

基金项目:河南省高等学校青年骨干教师资助项目(2014CGJS-292）

作者简介：李江涛（1978-），女，硕士，副教授 E-mail：lijtao19781@sina.com

参考文献：

\[1］孔敏,胡伟.工艺方案对高强平板冲压件回弹及补偿的影响\[J］.锻压技术,2023,48(10):75-80.

Kong M, Hu W. Influence of process scheme on springback and compensation for high strength flat stamping part \[J］. Forging & Stamping Technology, 2023,48(10):75-80.

\[2］ ElMaraghy H, Monostori L, Schuh G, et al. Evolution and future of manufacturing systems\[J］. CIRP Annals, 2021, 70(2): 635-658.

\[3］苑明海,黄涵钰,蔡仙仙,等.隐性扰动下智能车间资源重调度决策方法研究\[J］.制造技术与机床,2023(9):102-108,137.

Yuan M H, Huang H Y, Cai X X, et al. Decision method for intelligent workshop resource rescheduling under implicit disturbance \[J］. Intelligent Manufacturing, 2023(9):102-108,137.

\[4］ Arkhipov D I, Wu D, Wu T, et al. A parallel genetic algorithm framework for transportation planning and logistics management\[J］. Ieee Access, 2020, 8: 106506-106515.

\[5］于涛. 基于数学规划法的造纸制浆设备动态调度模型研究\[J］. 造纸科学与技术,2021,40(6):45-48.

Yu T. Research on dynamic scheduling model of pulping and papermaking equipment based on mathematical programming method \[J］. Paper Science and Technology, 2021,40(6):45-48.

\[6］ Bezdan T, Zivkovic M, Bacanin N, et al. Multi-objective task scheduling in cloud computing environment by hybridized bat algorithm\[J］. Journal of Intelligent & Fuzzy Systems, 2022, 42(1): 411-423.

\[7］ Hang S, Qi K Y, Miao L, et al. Research on workshop manufacturing resource scheduling control method based on industrial internet of things\[A］. Guangzhou Internet Society, 2020 International Conference on Computer Engineering and Application \[C］. Guangzhou, China: IEEE, 2020.

\[8］ Andrade-Pineda J L, Canca D, Gonzalez-R P L, et al. Scheduling a dual-resource flexible job shop with makespan and due date-related criteria\[J］. Annals of Operations Research, 2020, 291: 5-35.

\[9］ Tamssaouet K, Dauzère-Pérès S, Knopp S, et al. Multiobjective optimization for complex flexible job-shop scheduling problems\[J］. European Journal of Operational Research, 2022, 296(1): 87-100.

\[10］陈永灿,刘宇,周艳平.求解多目标柔性作业车间调度问题的混合自适应差分进化算法\[J］.制造技术与机床,2023(12):171-177.

Chen Y C, Liu Y, Zhou Y P. Hybrid adaptive differential evolution for multi-objective flexible job shop scheduling problem \[J］. Manufacturing Technology & Machine Tool, 2023(12):171-177.

\[11］亓祥波,马志强,王宏伟.求解PFSP的集成多策略教学优化算法\[J］.组合机床与自动化加工技术,2023(12):34-39.

Qi X B, Ma Z Q, Wang H W. Integrated multi-strategy teaching-learning-based optimization algorithm for solving PFSP \[J］. Modular Machine Tool & Automatic Manufacturing Technique, 2023(12):34-39.

\[12］Santos J, Rebelo P M, Rocha L F, et al. A based routing and scheduling modules for multiple agvs in an industrial scenario\[J］. Robotics, 2021, 10(2): 72.

\[13］段连浪. 求解多模态优化问题的小生境进化算法研究及应用\[D］. 武汉：华中科技大学,2023.

Duan L L. Research and Application of Niche Evolutionary Algorithm for Solving Multimodal Optimization Problems \[D］. Wuhan: Huazhong University of Science & Technology, 2023.

\[14］Sohail A. Genetic algorithms in the fields of artificial intelligence and data sciences\[J］. Annals of Data Science, 2023, 10(4): 1007-1018.

\[15］张惠彬,黄顺祥,刘峰,等.基于遗传算法的人员疏散路径优化控制\[J］.工业安全与环保,2020,46(10):24-28.

Zhang H B, Huang S X, Liu F, et al. Optimization of evacuation routes based on genetic algorithm \[J］. Industrial Safety and Environmental Protection, 2020,46(10):24-28.

\[16］李远锋,李章维,秦子豪,等.基于蒙特卡洛相似度遗传算法的运输问题研究\[J］.计算机科学,2020,47(10):215-221.

Li Y F, Li Z W, Qin Z H, et al. Study on transportation problem using monte carlo similarity based genetic algorithm \[J］. Computer Science, 2020,47(10):215-221.

\[17］姜鹏,方成刚,杨帆.GA-COA求解柔性作业车间多资源调度问题\[J］.机械设计与制造,2023(3):156-159,164.

Jiang P, Fang C G, Yang F. Hybrid genetic-coyote algorithm for multi-resource flexible jobshop scheduling problem \[J］. Machinery Design & Manufacture, 2023(3):156-159,164.

\[18］陈永灿,刘宇,周艳平.求解多目标柔性作业车间调度问题的混合自适应差分进化算法\[J］.制造技术与机床,2023(12):171-177.

Chen Y C, Liu Y, Zhou Y P. Hybrid adaptive differential evolution for multi-objective flexible job shop scheduling problem
［J］. Manufacturing Technology & Machine Tool, 2023(12):171-177.

服务与反馈：

【文章下载】【加入收藏】