English

中国农机化学报

中国农机化学报 ›› 2023, Vol. 44 ›› Issue (4): 187-194.DOI: 10.13733/j.jcam.issn.2095-5553.2023.04.026

• 农业智能化研究 • 上一篇    下一篇

基于改进蚁群算法的蔬菜大田无人农机路径优化

王海琛1, 2, 3,吴华瑞2, 3,朱华吉2, 3,缪祎晟2, 3,杨宝祝2, 3   

  1. 1. 沈阳建筑大学信息与控制工程学院,沈阳市,110168; 2. 国家农业信息化工程技术研究中心,北京市,100097;

    3. 北京农业信息技术研究中心,北京市,100097
  • 出版日期:2023-04-15 发布日期:2023-04-25
  • 基金资助:
    国家重点研发计划(2019YFD1101105);财政部和农业农村部:国家现代农业产业技术体系资助(CARS—23—D07);江苏大学农业装备学部项目(4111680005)

Path optimization of unmanned agricultural machinery in vegetable field based on improved ant colony algorithm

Wang Haichen1, 2, 3, Wu Huarui2, 3, Zhu Huaji2, 3, Miao Yisheng2, 3, Yang Baozhu2, 3   

  • Online:2023-04-15 Published:2023-04-25

摘要: 推进蔬菜机械化与无人化种植能够保障优良的蔬菜规模化种植技术效益,有力保证蔬菜质量与品质,有利于蔬菜规模化生产种植技术产业体系的发展。利用无人拖拉机作业GPS定位点集将实际农业作业区域转化为规则矩形,在此基础上建立以无人拖拉机总转弯距离最短为优化模型,采用蚁群算法对无人拖拉机耕地作业路径序列进行搜索。同时考虑到传统蚁群算法易陷入局部最优、全局搜索能力不足等问题,提出一种基于和声搜索策略的改进蚁群算法,通过引入sigmoid函数与和声搜索机制改善路径搜索能力,得到高质量耕地作业路径序列。将传统蚁群算法(AC)、精英蚁群算法(ELAC)作为对比算法,将传统梭形、回形作业方法作为路径对比作业方法,针对不同耕地作业规模进行无人拖拉机作业路径搜索试验。结果表明,本文算法得到的总转弯距离较梭形耕法降低35.53%~43.08%、较回形耕法降低2498%~86.88%。精英蚁群算法在小规模作业区域中性能较优,但随着蔬菜大田规模扩大,改进和声蚁群算法优化效果更明显。

关键词: 路径寻优, 无人农机, 排序优化, 蚁群算法

Abstract: Promoting vegetable mechanization and unmanned planting can guarantee the benefits of highquality vegetable largescale planting technology, and effectively guarantee the quality and quality of vegetables, which is conducive to the development of the industrial system of vegetable largescale production planting technology. This paper uses the GPS positioning point set for unmanned tractor operation to transform the actual agricultural operation area into a regular rectangle. On this basis, an optimization model with the shortest total turning distance of the unmanned tractor is established, and the ant colony algorithm is used to search the path sequence of unmanned tractor cultivated land. At the same time, considering that the traditional ant colony algorithm is easy to fall into the local optimum and the global search ability is insufficient, an improved ant colony algorithm based on the harmony search strategy is proposed. The sigmoid function and the harmony search mechanism are introduced to improve the path search ability and obtain high sequence of quality farmland working paths. In this paper, the traditional ant colony algorithm (AC), the elite ant colony algorithm (ELAC) and the shuttle and back operation methods are used as comparison algorithms, and the operation path search experiment of unmanned tractors is carried out for different farmland operation scales. The test results show that the total turning distance obtained by the algorithm in this paper is reduced by 35.53%-43.08% compared with the shuttle tillage method, and reduced by 24.98%-86.88% compared with the return tillage method. The elite ant colony algorithm has better performance in smallscale operation areas, but as the scale of vegetable fields expands, the optimization effect of the improved harmony ant colony algorithm is more obvious.

Key words: path optimization, unmanned agricultural machinery, ranking optimization, ant colony algorithm

中图分类号: