欢迎您访问《智慧农业（中英文）》官方网站！ English
智慧农业

Smart Agriculture ›› 2020, Vol. 2 ›› Issue (4): 137-148.doi: 10.12133/j.smartag.2020.2.4.202011-SA006

• 专刊--农业机器人与智能装备 • 上一篇    下一篇

基于订单位置聚类的雏鸡配送车辆调度优化模型

陈栋1,2(), 陈天恩1,2(), 姜舒文1, 张驰1, 王聪1, 鲁梦瑶1   

  1. 1.国家农业信息化工程技术研究中心，北京 100097
    2.农芯（南京）智慧农业研究院，江苏 南京 211800
  • 收稿日期:2020-11-25 修回日期:2020-12-22 出版日期:2020-12-30
  • 基金资助:
    北京市科技计划课题(Z181100009818005)
  • 作者简介:陈 栋（1988－），男，博士，助理研究员，研究方向为农业数据集成与农产品供应链智能算法研究。E-mail：chend@nercita.org.cn。
  • 通信作者:

Optimal Model of Chicken Distribution Vehicle Scheduling Based on Order Clustering

CHEN Dong1,2(), Tian'en CHEN1,2(), JIANG Shuwen1, ZHANG Chi1, WANG Cong1, LU Mengyao1   

  1. 1.National Engineering Research Center for Information Technology in Agriculture(NERCITA), Beijing 10097, China
    2.Agricultural Core (Nanjing) Institute of Intelligent Agriculture, Nanjing 211800, China
  • Received:2020-11-25 Revised:2020-12-22 Online:2020-12-30

在线阅读

447

知网下载

本地下载

705

摘要：

为解决大型禽业企业物流订单位置跨度大、配送车辆调度工作人工参与度高、雏鸡配送成本高的问题，本研究结合车辆路径优化问题求解思路，提出了基于订单位置聚类的雏鸡配送车辆调度优化模型。模型通过引入K-means聚类算法，实现了基于订单位置的配送单元划分方法，并基于肘部法则与轮廓系数法设计了自动化订单位置聚类流程，实现了订单配送单元的自主式划分。在划分的各组订单基础上，以配送成本最优作为目标函数，建立雏鸡配送车辆调度优化模型，并结合改进的遗传算法进行求解。研究采用北京某禽业企业实际订单数据，对订单未聚类情况下的整体调度优化与聚类分组情况下的调度优化两种情况的结果进行了对比分析，结果表明订单聚类分组情况下，优化模型使配送车辆平均每天总里程比订单未聚类情况降低69.84%，可以得出，加入聚类算法的订单分组优化更适合实际订单位置跨度大、订单数量多的车辆调度场景。基于以上研究，研发设计了适用于雏鸡配送的车辆调度优化服务系统，实现了订单自动化聚类、配送车辆调度优化、定制化模型服务等功能，通过模型的实际应用，达到了为禽业企业提供智能化配送车辆调度优化服务的目的，切实提高了企业运行效率，降低了企业配送成本。

关键词: 雏鸡配送, 车辆调度优化模型, K-means聚类算法, 遗传算法, 智慧畜禽, 定制化模型服务

Abstract:

In order to solve the problems that orders are widely distributed, scheduling of distribution vehicle needs a lot of manpower,and high cost of chicken distribution in large-scale poultry enterprise, in this research, combined with the idea of solving vehicle routing optimization problem, a chicken distribution vehicle scheduling optimization model based on order location clustering was proposed. By introducing the K-means clustering algorithm, a distribution unit division method based on order location was implemented, an automated order location clustering process based on the elbow rule and contour coefficient method to realize the autonomous division of order distribution units was designed. On the basis of the divided groups of orders, the optimal delivery cost was taken as the objective function to establish a chicken delivery vehicle scheduling optimization model, and the model was solved with an improved genetic algorithm.The actual order data of a poultry company in Beijing was used to compare the results of the overall scheduling optimization in the case of orders without clustering and the scheduling optimization in the case of with clustering grouping. The results showed that the model in the case of orders with clustering could reduce the average daily mileage of delivery vehicles by 69% compared with orders without clustering, it could be seen that the optimization of order grouping with clustering algorithm was more suitable for vehicle scheduling scenarios with a large actual order position span and a large number of orders. Based on the above research, a vehicle scheduling optimization service system was developed, functions such as automatic order clustering, delivery vehicle scheduling optimization were realized, and model service application programming interface was customized.The practical application results of the model showed that, the average total mileage per day decreased by 5.04% compared with manual routing, the manual routing time took 20 to 30 minutes per day, and the average time for the model to complete the routing was 14.49 s. The goal of providing intelligent delivery vehicle scheduling optimization services for poultry industry enterprises has been achieved, which could effectively improve the operation efficiency and reduce the distribution cost of the poultry enterprise.

Key words: chicken delivery, vehicle scheduling optimization model, K-means clustering algorithm, genetic algorithm, smart poultry, API

中图分类号: 

京ICP备09089781号-37