基于深度神经网络的智慧卷烟物流配送线路自适应调度算法  

Adaptive scheduling algorithm of intelligent cigarettelogistics distribution line based on deep neural network

作　　者：张超 胡鹏 杨明 全鹏 陈辉 汪明 Zhang Chao;Hu Peng;Yang Ming;Quan Peng;Chen Hui;Wang Ming("Internet+Tobacco"Fusion Innovation Laboratory,Hubei Provincial Tobacco Monopoly Administration(Company),Hubei Wuhan,430030,China;Science and Technology Information Center of Shiyan Company,Hubei Tobacco Company,Hubei Shiyan,442099,China;Logistics Management Office,Hubei Provincial Tobacco Monopoly Administration(Company),Hubei Wuhan,430030,China;Shiyan Company Logistics and Distribution Center,Hubei Tobacco Company,Hubei Shiyan,442099,China)

机构地区：[1]湖北省烟草专卖局(公司)“互联网+烟草”融合创新实验室,湖北武汉430030 [2]湖北省烟草公司十堰市公司科技信息中心,湖北十堰442099 [3]湖北省烟草专卖局(公司)物流管理处,湖北武汉430030 [4]湖北省烟草公司十堰市公司物流配送中心,湖北十堰442099

出　　处：《机械设计与制造工程》2023年第12期99-103,共5页Machine Design and Manufacturing Engineering

基　　金：湖北省烟草专卖局(公司)科技创新项目(027Y2021-046)。

摘　　要：针对物流配送线路路况难以预测、物流配送里程较长、调度过程难以协调的问题,提出基于深度神经网络的智慧卷烟物流配送线路自适应调度算法。根据智慧卷烟物流配送要求,以最短配送总里程为目标建立物流调度数学模型。利用知识库和果蝇优化算法,根据线路动态调度规则,引入深度神经网络,优化设计配送区域路况预测模型。以当前路段交通状况预测结果为依托,结合分时带权交通网络模型,得到配送线路自适应调度结果。实验结果表明:该方法相比传统算法使得智慧卷烟物流配送里程分别减少了38.62%、45.01%,实现了物流配送成本的降低。Aiming at the problems that the road condition of logistics distribution line is difficult to predict,the logistics distribution mileage is long and the scheduling process is difficult to coordinate,an adaptive scheduling algorithm of intelligent cigarette logistics distribution line based on deep neural network is proposed.According to the requirements of intelligent cigarette logistics distribution,a logistics scheduling mathematical model is established with the shortest total distribution mileage as the goal.Using the knowledge base and fruit fly optimization algorithm,the route dynamic scheduling rules are selected,and the deep neural network is introduced to optimize the design of the road condition prediction model in the distribution area.Based on the prediction results of current road traffic conditions,combined with the time-sharing and weighted traffic network model,the adaptive scheduling results of distribution lines are obtained.The experimental results show that this method reduces the mileage of intelligent cigarette logistics distribution by 38.62%and 45.01%,reduces the logistics distribution cost.

关 键 词：深度神经网络 智慧卷烟 物流 配送线路 自适应调度 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]