基于Android系统的蔬菜智能耕作装置设计与试验
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:

国家自然科学基金项目(51505130)、国家重点研发计划项目(2016YFD0700103)和河南省科技创新杰出人才项目(184200510017)


Design and Experiment of Intelligent Farming Device for Vegetables Based on Android
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为了提高蔬菜生产智能化水平,针对蔬菜生产集约化程度不高、自动化水平低及耕作耗时耗力等问题,集机械设计、压力传感、无线传输、互联网通信及Android手机终端控制等技术,设计了蔬菜智能耕作装置。该装置包括耕作机械部件与以STM32单片机为核心的控制系统,并基于Android系统开发了移动客户端软件,可实现耕作信息远程查看及操控功能。根据Android客户端的耕作指令,选择不同功能的末端执行器以完成相应的动作:通过电容式土壤水分检测功能,实现土壤水分信息监测;通过播种部件以及龙门架定位,完成定位定量播种;通过液态物料投放部件以及设置在液路管道接口处的PVDF压力传感器,实现液态物料投放堵塞及流量监测,完成液态物料精量投放;通过CCD摄像头获取作物图像信息,并基于BP神经网络开发了杂草识别算法,实现杂草识别。试验结果表明:该智能耕作装置可实现定位定量播种功能,株距平均合格率可达95.13%,平均误播率为4.86%;液态物料投放功能较为稳定,且均匀性较好,最大投放误差不超过5.4g。

    Abstract:

    In order to promote the development of mechanization of vegetable production and increase the level of intelligent, an intelligent farming device for vegetables was designed based on mechanical design, pressure sensing, WiFi transmission, internet communications and Android mobile phone terminal control. The device included a farming mechanical component and a control system based on STM32 MCU, a mobile client software was developed based on Android, which can realize the remote viewing and manipulation functions. According to the farming instructions of the Android client, the end effector can select different functional heads to complete the corresponding farming action;through the capacitive soil moisture detection function head to monitor the soil moisture;positioning and quantitative sowing was performed through the sowing function head and gantry positioning;through the liquid material function head and PVDF pressure sensor installed at the liquid pipeline interface, to achieve liquid material delivery jam and flow monitoring, complete delivery of liquid material precision;the crop image information was acquired by CCD camera, and the weed identification algorithm was developed based on BP neural network to realize weed identification. The test results showed that the qualified rate of the plant spacing can reach 9513%, and the rate of misuse was 4.86%;the liquid material delivery function was relatively stable and uniform, and the maximum error was no more than 5.4g.

    参考文献
    相似文献
    引证文献
引用本文

姬江涛,李明勇,金鑫,赵凯旋,吴霭玲,孙经纬.基于Android系统的蔬菜智能耕作装置设计与试验[J].农业机械学报,2018,49(8):33-41,118. JI Jiangtao, LI Mingyong, JIN Xin, ZHAO Kaixuan, WU Ailing, SUN Jingwei. Design and Experiment of Intelligent Farming Device for Vegetables Based on Android[J]. Transactions of the Chinese Society for Agricultural Machinery,2018,49(8):33-41,118

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2018-05-06
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2018-08-10
  • 出版日期: