酿酒葡萄生长全过程多任务多农机调度研究  

Study on Multi Task and Multi Agricultural Machinery Scheduling in the Whole Process of Wine Grape Growth

作　　者：李雯[1] 倪锡涛 Li Wen;Ni Xitao(School of Management,Jiangsu University,Zhenjiang 212013,China)

机构地区：[1]江苏大学管理学院,江苏镇江212013

出　　处：《农机化研究》2024年第5期262-268,共7页Journal of Agricultural Mechanization Research

基　　金：国家重点研发计划项目(2019YFD1002500)。

摘　　要：针对酿酒葡萄生长全过程中存在多任务多农机调度的需求,而传统调度研究很少有针对酿酒葡萄的多农机多任务协同作业研究。为此,结合作业田块相关信息与农机信息,基于车辆路径规划问题(Vehicle Routing Problem,VRP),以成本最优为目标构建酿酒葡萄生长全过程多任务多农机调度模型,提出改进自适应遗传算法(Improved Adaptive Genetic Algorithm,IAGA)进行运算求解;结合宁夏贺兰山东麓酿酒葡萄产区实际作业田块信息与农机信息进行仿真实验,并与传统遗传算法(Genetic Algorithm,GA)进行对比。研究结果表明:相比于GA,IAGA有着较强的收敛性,不易陷入局部最优,在调度结果上,调度总时间上能够缩短2.22%,在农机调度总成本降低2.32%,在酿酒葡萄实际作业中能够极大地节约作业时间并降低作业成本。In view of the demand of multi task and multi agricultural machinery scheduling in the whole process of wine grape growth,there is little research on multi agricultural machinery and multi task collaborative operation for wine grape in traditional scheduling research.Based on the vehicle routing problem(VRP),this paper constructs a multi task and multi agricultural machinery scheduling model for the whole process of wine grape growth,and puts forward an improved adaptive genetic algorithm(IAGA)to solve it;Combined with the actual operation field information and agricultural machinery information in the eastern foot of Helan wine grape production area in Ningxia,the simulation experiment is carried out,and compared with the traditional genetic algorithm(GA).The results show that compared with GA,IAGA has strong convergence and is not easy to fall into local optimization.In terms of scheduling results,the total scheduling time can be shortened by 2.22%,and the total scheduling cost of agricultural machinery can be reduced by 2.32%.In the actual operation of wine grape,IAGA can greatly save the operation time and cost and reduce the operation cost.

关 键 词：农机调度 改进自适应遗传算法 多机协同作业 算法 时间窗 

分 类 号：S232.4[农业科学—农业机械化工程]