融合启发式搜索的改进极快决策树算法在多规格货物智能混合装载中的应用  

Application of Intelligent Mixed Loading of Multi-specification Cargo Based on Extremely Fast Decision Tree Heuristically Search Algorithm

作　　者：李伟 杨超宇[1] 孟祥瑞[1] LI Wei;YANG Chao-yu;MENG Xiang-rui(School of Economics and Management,Anhui University of Science and Technology,Huainan 232001,China)

机构地区：[1]安徽理工大学经济与管理学院,淮南232001

出　　处：《科学技术与工程》2020年第36期15074-15080,共7页Science Technology and Engineering

基　　金：国家自然科学基金(61873004,51874003);安徽教育厅人文社会科学研究项目(SK2017A0098);安徽理工大学博士基金(11892)。

摘　　要：针对多规格货物装载效率较低问题,提出一种融合启发式搜索的改进极快决策树智能装箱算法,该算法首先计算并择优选取样本信息熵,然后构建生成货物装箱决策树模型,基于启发式搜索方法对货物装载后的剩余空间进行合并再利用。通过保证决策树每个节点装入货物体积最大,对待装货物进行快速决策。最后,基于七组异构性逐渐增强的货物数据对算法进行仿真实验。结果表明:本算法在保证较高集装箱利用率的情况下实现了快速装箱。Concerning the problem that the cargo low efficiency problem of many specifications,a fusion of heuristic search was proposed to improve fast packing and intelligent decision tree algorithm.Firstly,both the sample information for calculation and the optimal entropy were selected to ensure maximum volume into the container.Secondly,a decision tree model was built for cargo packing.Based on heuristic search,the remaining space was merged and reused after loading goods.By ensuring each node of the decision tree has the largest volume of goods,quick decisions were made on loaded goods.Lastly,based on seven groups of cargo data with increasing heterogeneity,the algorithm was simulated.The simulation experimental results show that the algorithm can achieve fast loading while ensuring a higher utilization rate of containers.

关 键 词：集装箱装载 智能装载 极快决策树 启发式算法 

分 类 号：U294.3[交通运输工程—交通运输规划与管理]