摘要
为了提高农业生产效率,以提高多台无人驾驶拖拉机的协同作业为研究目标,构建了农业生产多台无人驾驶拖拉机的路径优化模型。同时,根据拖拉机驾驶参数优化总转弯时间和总作业时间的目标函数,提出了适用于多台拖拉机路径优化的自适应精英差分进化(AEDE)算法,并通过改进微分进化算法进行求解,采用精英选择策略选择最优运行方案。以果园为研究对象开展田间验证试验,结果表明:与传统的差分进化算法(Differential Evolution, DE)相比,基于AEDE优化后的多拖拉机路径优化方案下拖拉机总转弯时间和总作业时间分别减少了3.85%和1.46%。由此表明,基于AEDE智能算法可以优化多台拖拉机田间操作路径,显著提高农业生产效率工作效率,降低拖拉机田间运行时间。研究结果可为提升农业生产智能化管理提供理论借鉴与技术参考。
In order to improve the efficiency of agricultural production,this study takes improving the cooperative operation of multiple unmanned tractors as the research objective,constructs the path optimization model of multiple unmanned tractors in agricultural production,optimizes the objective functions of total turning time and total operation time according to the tractor driving parameters,proposes the adaptive elite differential evolution(AEDE)algorithm applicable to the path optimization of multiple tractors,and improves the differential evolutionary algorithm is solved and the optimal operation scheme is selected by elite selection strategy.The results show that the total tractor rotation time and total operation time are reduced by 3.85%and 1.46%,respectively,under the AEDE-based multi-tractor path optimization scheme compared with the traditional Differential Evolution(DE)algorithm.The results show that the AEDE-based intelligent algorithm can optimize multiple tractor field operation paths,which can significantly improve agricultural production efficiency work efficiency and reduce tractor field operation time.The research results aim to provide theoretical reference and technical reference for enhancing the intelligent management of agricultural production.
作者
侯晓晓
王蒙
Hou Xiaoxiao;Wang Meng(Huanghe Jiaotong University,Wuzhi 454950,China;Shihezi University,Shihezi 832000,China)
出处
《农机化研究》
北大核心
2024年第12期240-244,249,共6页
Journal of Agricultural Mechanization Research
基金
河南省社科联调研项目(SKL-2021-2401)
黄河交通学院教学建设项目(HHJTXY-2022kczyk050)
石河子大学青年创新人才培育项目(CXPY202120)。
关键词
无人拖拉机
路径优化
农业管理
差分进化算法
适应性参数
unmanned tractor
path optimization
agricultural management
differential evolutionary algorithm
adaptive parameters