|本期目录/Table of Contents|

[1]孙浩宇,王云超,温圣兴,等.基于动态混合PSO-GA算法的AGV调度系统优化[J].集美大学学报(自然科学版),2026,31(5):581-592.
　SUN Haoyu,WANG Yunchao,WEN Shengxing,et al.Optimization of AGV Scheduling System Based on Dynamic Hybrid PSO-GA Algorithm[J].Journal of Jimei University,2026,31(5):581-592.
点击复制

基于动态混合PSO-GA算法的AGV调度系统优化(PDF)
分享到：

《集美大学学报（自然科学版）》[ISSN:1007-7405/CN:35-1186/N]

卷:
第31卷
期数:
2026年第5期
页码:
581-592
栏目:
船海与交通运输工程
出版日期:
2026-09-28

文章信息/Info

Title:
Optimization of AGV Scheduling System Based on Dynamic Hybrid PSO-GA Algorithm
作者:
孙浩宇; 王云超; 温圣兴; 吴培廷; 许申奥; 刘金阳
(集美大学海洋装备与机械工程学院，福建 厦门 361021)
Author(s):
SUN Haoyu; WANG Yunchao; WEN Shengxing; WU Peiting; XU Shen’ao; LIU Jinyang
(College of Mechanical and Energy Engineering,Jimei University,Xiamen,361021,China)
关键词:
AGV调度; 粒子群优化; 遗传算法; 动态混合策略; 多目标优化
Keywords:
AGV scheduling; particle swarm optimization; genetic algorithm; dynamic hybrid strategy; multi-objective optimization
分类号:
-
DOI:
-
文献标志码:
A
摘要:
针对制造车间自动导引车（AGV）调度中存在收敛速度慢、易陷入局部最优及多目标难以协同优化等问题，本文提出一种动态混合频率的粒子群遗传（PSO-GA）优化算法。该算法构建了以调度成本、任务延误及响应速度为核心的多目标加权模型，并通过分阶段动态调整种群混合频率与个体交换比例，有效平衡了全局探索与局部开发能力。基于企业无尘车间的真实排产数据，开展了所提算法分别与标准遗传算法（GA）、标准粒子群算法（PSO）的对比仿真实验。结果表明：与GA算法相比，本文算法将AGV需求量从8台降至5台（减少37.5%），目标函数值降低，平均任务响应时间从2.86 min缩短至1.29 min（缩短54.9%），紧急任务响应时间低至0.93 min，同时依然保证了100%的任务准时交付率；与PSO算法相比，本文算法在寻得更优解（目标函数值降低2.3%）的同时有效避免了早熟收敛。本文算法显著提升了AGV系统的调度效率、资源利用率与动态适应性。
Abstract:
Aiming at the problems of slow convergence,susceptibility to local optima,and difficulty in coordinating multi-objective optimization in automated guided vehicle (AGV) scheduling for manufacturing workshops,this paper proposed a dynamic hybrid frequency particle swarm optimizationgenetic algorithm (PSO-GA).The algorithm constructed a multi-objective weighted model focusing on scheduling cost,task delay,and response speed,and achieves an effective balance between global exploration and local exploitation by dynamically adjusting the population hybrid frequency and individual exchange ratio in phases.Based on the real production scheduling data of an enterprise’s dust-free workshop,comparative simulation experiments were carried out between the proposed algorithm,the standard genetic algorithm (GA) and the standard particle swarm optimization (PSO) algorithm.The results showed that,in comparing with the GA,the proposed algorithm reduced the AGV demand from 8 to 5 (a decrease of 37.5%),lowered the objective function value,shortened the average task response time from 2.86 to 1.29 minutes (a reduction of 54.9%),achieved an emergency task response time as low as 0.93 minutes,and accomplished 100% of tasks without delay.Compared with PSO,it finds a better solution (a 2.3% reduction in the objective function value) while effectively avoiding premature convergence.The algorithm significantly improves the scheduling efficiency,resource utilization,and dynamic adaptability of the AGV system.

参考文献/References:

相似文献/References:

[1]曹雪莲,陈水利.基于粒子群优化及多结构估计的ASIFT特征提取算法[J].集美大学学报(自然科学版),2013,18(2):139.
　CAO Xue-lianCHEN Shui-li.ASIFT Research Based on Particle Swarm Optimization and Multi -Structure Estimating[J].Journal of Jimei University,2013,18(5):139.
[2]李浩天,戴乐阳,王永坚,等.改进粒子群优化的铁谱图像聚类分割[J].集美大学学报(自然科学版),2025,30(1):95.
　LI Haotian,DAI Leyang,WANG Yongjian,et al.Clustering Segmentation of Ferrograph Images Based on Improved Particle Swarm Optimization[J].Journal of Jimei University,2025,30(5):95.

备注/Memo

备注/Memo:
更新日期/Last Update: 2026-11-01