基于混合遗传蚁群算法的异类货物装载研究  

Heterogeneous Cargo Loading Based on Hybrid Genetic Ant Colony Algorithm

作　　者：赵剑飞 许德章[1,2] ZHAO Jianfei;XU Dezhang(School of Artificial Intelligence,Anhui Polytechnic University,Wuhu Anhui 241000,China;Wuhu Anpu Robot Industry Technology Research Institute,Wuhu Anhui 241000,China)

机构地区：[1]安徽工程大学人工智能学院,安徽芜湖241000 [2]芜湖安普机器人产业技术研究院有限公司,安徽芜湖241000

出　　处：《淮阴工学院学报》2024年第5期61-68,共8页Journal of Huaiyin Institute of Technology

基　　金：国家自然科学基金项目“工业机器人3D全结构刚柔耦合交互特性视觉测量方法研究”(52005003)。

摘　　要：针对目前快递运输作业依靠装载工经验、车辆运输及货物配送效率难以充分发挥的问题,提出了一种混合遗传蚁群装箱算法。根据装载货物尺寸、包装形式、配送优先顺序以及车辆长、宽、高等约束条件,采用空间启发式算法确定装载策略,运用改进遗传算法生成优质种群,为蚁群提供初始循迹方向,通过优化蚁群算法迭代更新寻找最佳装箱方案,采用三维数字化建模技术,生成货物码放顺序动画,实现装载工艺的可视化,引导工人完成装载作业。通过货物装载仿真实验,对比遗传算法、混合遗传模拟退火算法与改进差分进化算法,混合遗传蚁群算法运行时间短且车箱利用率高,验证了该算法的可行性和有效性。Aiming to address the issues,which heavily rely on the experience of loading workers,vehi⁃cle transportation,and difficult to make full ues of cargo delivery efficience,a hybrid genetic ant colo⁃ny packing algorithm has been proposed.This algorithm considers constraints such as the size of load⁃ed goods,packaging format,delivery priority sequence,and vehicle dimensions(length,width,height).It utilizes spatial heuristic algorithms to determine loading strategies,employs an improved genetic algo⁃rithm to generate a high-quality population for the ant colony,and optimizes the ant colony algorithm iteratively to find the best packing solution.Additionally,it uses three-dimensional digital modeling technology to create an animated sequence depicting the order of cargo placement,making the loading process visual and guiding workers in completing the loading operations.Through cargo loading simula⁃tion experiments,a comparison between genetic algorithms,hybrid genetic simulated annealing algorithms,and improved differential evolution algorithms revealed that the hybrid genetic ant colony algorithm had shorter operational times and higher container utilization rates,validating the feasibility and effective⁃ness of this algorithm.

关 键 词：货物装载 启发式算法 遗传算法 蚁群算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]