基于机器人的生猪健康养殖智能监控系统设计  

Design of intelligent monitoring system for healthy breeding of pigs based on robotics

作　　者：刘艳昌[1] 赵海生 李泽旭 张志霞[1] 左现刚[1] 李国厚[1] Liu Yanchang;Zhao Haisheng;Li Zexu;Zhang Zhixia;Zuo Xiangang;Li Guohou(Department of Information Engineering,Henan Institute of Science and Technology,Xinxiang,453003,China)

机构地区：[1]河南科技学院信息工程学院,河南新乡453003

出　　处：《中国农机化学报》2021年第8期187-195,共9页Journal of Chinese Agricultural Mechanization

基　　金：河南省科技攻关项目(162102210292、202102210388);国家级大学生创新训练计划项目(202010467003)。

摘　　要：为提高生猪养殖环境质量和行为识别率,克服规模化养殖过程中采用人工巡检生猪异常行为特征和监测养殖环境参数存在识别效率低、准确性差和劳动强度大等问题,设计一种以轨道式机器人为采集终端的生猪健康养殖智能监控系统。系统以FPGA控制器为硬件核心,结合猪只体表特征与环境感知传感器、智能控制、图像处理和无线通信技术,构建生猪异常行为与异常环境全景和局部两级联动监测平台,实现对生猪异常行为和环境参数的全方位观察、识别和数据采集功能,提高生猪养殖过程的智能化管理水平。试验结果表明,该系统能够按照预设指令自动、快速地依次对选取猪舍猪只个体的生长情况、行为特征和养殖环境信息进行自动采集,异常行为识别率可达93.5%,停车定位精度误差为±12 mm。该研究有利于技术人员快速、准确获取生猪生长环境和健康状况信息,为生猪异常环境及时调控、异常行为快速诊断、疫病防治和疫情预警提供科学依据。In order to improve the quality of pig breeding environment and behavior recognition rate,and overcome the problems of low recognition efficiency,poor accuracy,and high labor intensity in large-scale breeding using manual inspection of abnormal behavior characteristics of live pigs and monitoring of breeding environment parameters,an intelligent monitoring system for pig health breeding based on the orbital robot was designed.The system consisted of an FPGA controller as the hardware core,combined with pig body surface characteristics and environmental sensing sensor,intelligent control,image processing,and wireless communication technology to construct a panoramic and local two-level linkage monitoring platform for abnormal behavior and abnormal environment of pigs.The omnidirectional observation,identification,and data collection functions of abnormal pig behavior and environmental parameters improved the intelligent management level of the pig breeding process.The experimental results showed that the system can automatically and quickly collect the growth,behavior characteristics,and breeding environment information of individual pigs in the selected pig house according to the preset instructions.The abnormal behavior recognition rate reached 93.5%,and the parking positioning accuracy error was±12 mm.The research was conducive for technical personnel to quickly and accurately obtain information about the growth environment and health status of pigs and provide a scientific basis for timely regulation of abnormal environments,rapid diagnosis of abnormal behaviors,disease prevention,and early warning of pigs.

关 键 词：机器人 健康养殖 智能监控 FPGA 行为识别 

分 类 号：S82[农业科学—畜牧学] TP273[农业科学—畜牧兽医]