日光温室环境因子预测模型及应用——基于BP神经网络  

Establishment and Application of Environmental Factor Model of Solar Greenhouse—Based on BP Neural Network

作　　者：宋财柱 塔娜[1] 闫彩霞 孙云峰[1,2] 甄琦[2] 李晓凯 Song Caizhu;Ta Na;Yan Caixia;Sun Yunfeng;Zhen Qi;Li Xiaokai(College of Mechanical and Electrical Engineering,Inner Mongolia Agricultural University,Hohhot 010018,China;College of Energy and Transportation Engineering,Inner Mongolia Agricultural University,Hohhot 010018,China)

机构地区：[1]内蒙古农业大学机电工程学院,呼和浩特010018 [2]内蒙古农业大学能源与交通工程学院,呼和浩特010018

出　　处：《农机化研究》2024年第10期175-179,186,共6页Journal of Agricultural Mechanization Research

基　　金：国家自然科学基金项目(61663038);内蒙古自然科学基金项目(2022MS03040)。

摘　　要：为探讨北方日光温室内空气温湿度的变化规律,预测其变化趋势,进而确定合理的调控措施,采用L-M算法建立BP神经网络预测模型;选择S型函数作为网络激活函数,建立一种适用于北方日光温室空气温湿度环境因子的模拟预测模型。选取正常生产的日光温室为试验基地进行数据采集,采用皮尔逊相关系数确定模拟预测模型的输入因子,从1个月1440组实测数据中选取前29天的数据进行训练,对最后一天预测出的数据进行验证。研究结果表明:分段预测的预测值与实测值的符合度值大于全天预测,且分段预测的符合度大于0.99,均方根误差小于0.4,模型可用于模拟和预测北方日光温室大棚内空气温度与湿度的变化趋势,具有良好效果。In order to explore the change law of air temperature and humidity in the northern solar greenhouse,predict its change trend,and then take reasonable control measures,the BP neural network prediction network is established by using L-M algorithm,and the S-type function is selected as the network activation function to establish a simulation prediction model for the environmental factors of air temperature and humidity in the northern solar greenhouse.The normal production solar greenhouse is selected as the test base for data collection.The Pearson correlation coefficient is used to determine the input factor of the simulation prediction model.The data of the first 29 days are selected from 1440 groups of measured data in a month for training.The predicted data are verified with the data of the last day.The results show that the consistency between the predicted value and the measured value of the segmented prediction is greater than that of the whole day prediction,and the consistency of the segmented prediction is greater than 0.99,and the root mean square error is less than 0.4.The model can be used to simulate and predict the change trend of the air temperature and humidity in the northern solar greenhouse,and the prediction result is good.

关 键 词：日光温室 环境因子 BP神经网络 预测模型 

分 类 号：S625.5[农业科学—园艺学]