基于物联网与人工神经网络的温室监控方案  

Greenhouse Monitor Approach Based on the Internet of Things and Artificial Neural Network

作　　者：杨俊成[1] 李淑霞[1] 李亮 YANG Jun-cheng;LI Shu-xia;LI Liang(Department of Electronics and Information Engineering,Henan Polytechnic Institute,Nanyang 473000,China;College of Mathematics and Information Science,Hebei Normal University,Shijiazhuang 050024,China)

机构地区：[1]河南工业职业技术学院电子信息工程学院,河南南阳473000 [2]河北师范大学数学与信息科学学院,石家庄050024

出　　处：《控制工程》2020年第9期1649-1656,共8页Control Engineering of China

基　　金：河南省高等学校青年骨干教师培养计划基金项目(2018GGJS230);全国高等院校计算机基础教育研究会纵向课题(2016GHB02003);河南工业职业技术学院青年骨干教师培养计划。

摘　　要：为提高观叶植物温室的自动化水平,根据物联网采集的温室微气候数据与植物图像,设计了基于人工神经网络预测的温室监控方案。首先,设计了基于物联网的温室微气候检测系统与植物图像采集系统,设计了图像处理算法来提取植物的叶区域;然后,采用两因素方差方法分析微气候因素与观叶植物叶区域生长速度的关系,由此确定神经网络的输入量与输出量;最终,使用采集的历史微气候数据对神经网络进行训练,获得神经网络的最优模型参数,建立微气候因素的预测模型。实验结果表明,该系统能够准确地预测出温室微气候的变化状态,使温室微气候满足兰花的最优生长条件。In order to improve the automatic level of greenhouse of leaf-viewed plants, a greenhouse monitoring approach based on the artificial neural network is proposed, according to the micro-climate data and plant images acquired through Internet of Things. Firstly, the acquisition systems of greenhouse micro-climate and plant images based on Internet of Things are designed, and an image processing algorithm is designed to abstract the leaf area;then, the two-way ANOVA method are adopted to analyze the relationship between the micro-climate factors and the leaf area growth rate of leaf-view plants, thus the input variables and the output variables are determined;lastly, the historical micro-climate data is used to train the artificial neural network to get the optimal model parameters of artificial neural network, and the prediction model of micro-climate factors are constructed. The experimental results show that the proposed prediction model can predict the micro-climate variation of greenhouse, and make the micro-climate of greenhouse to satisfy the optimal growth conditions of orchids.

关 键 词：物联网 温室监控 观叶植物 图像处理 人工神经网络 深度学习 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]