摘要
为实现羊只日常体重的无应激快速精确检测,提高羊只福利化水平和羊场智能化程度,结合经验模态分解(EMD)和平均值处理动态称重算法,设计出一套羊只动态称重分群系统且对两种算法进行试验对比。结果表明:在相同平均用时8.4 s时,EMD算法平均误差1.1%,平均值算法平均误差2.7%,前者优于后者。同时本系统在10 s内,可顺利完成羊只无应激称重分群工作,具有一定应用价值。
In order to realize the rapid and accurate detection of sheep’s daily weight without stress and improve the welfare level of sheep and the intelligence degree of sheep farm, this paper combined the empirical mode decomposition(EMD) and the mean value processing dynamic weighing algorithm to design a set of sheep dynamic weighing clustering system and carried out experimental comparison of the two algorithms. The results show that the average error of EMD algorithm is 1.1% and the average error of average algorithm is 2.7% when the same average time is 8.4 s, the former is better than the latter.At the same time, the system can successfully complete the no-stress weighing and grouping of sheep within 10 s, which has certain application value.
作者
王奎
武佩
宣传忠
王昊毅
朱晓波
Wang Kui;Wu Pei;Xuan Chuanzhong;Wang Haoyi;Zhu Xiaobo(College of Mechanical and Electrical Engineering of Inner Mongolia Agricultural University,Inner Mongolia Engineering Research Center for Intelligent Facilities in Prataculture and Livestock Breeding,Hohhot,010018,China)
出处
《中国农机化学报》
北大核心
2019年第9期164-170,共7页
Journal of Chinese Agricultural Mechanization
基金
国家自然基科学基金项目(11364029、31860666)
内蒙古自治区研究生教育创新计划资助项目(S20171012904)
关键词
无应激称重
分群
畜牧机械
no stress weighing
clustering
animal husbandry machinery
