摘要
为构建较准确的日光温室温湿度预测模型,于2011—2014年冬季(1月、2月、12月)在天津市宝坻区开展温室内外环境监测试验,并建立3种天气类型(晴、多云、阴)下3个时段(0—8时、8—17时、17—23时)逐步回归与BP神经网络温室内温湿度预测模型。结果表明;(1)温室内气温逐步回归模型9种情况下模拟值与实际值的绝对误差小于3℃的平均准确率(≤3℃)为88%,平均均方根误差(RMSE)为2℃;BP神经网络模型9种情况下模拟值与实际值的绝对误差小于3℃的平均准确率(≤3℃)为94%,平均均方根误差(RMSE)为1.6℃。应用BP神经网络建立的气温预测模型相对更为准确稳定;(2)相对湿度逐步回归模型9种情况下模拟值与实际值的绝对误差小于6%的平均准确率(≤6%)为81%,平均均方根误差(RMSE)为5.7%;BP神经网络模型9种情况下模拟值与实际值的绝对误差小于6%的平均准确率(≤6%)为80%,平均均方根误差(RMSE)为6.7%。2类模型均不适宜预测8—17时日光温室相对湿度,而17—23时与0—8时应用逐步回归建立的湿度预测模型相对更准确稳定。
To build a more accurate model for predicting temperature and humidity in solar greenhouse, amicroclimatic observing experiment was carried out at Baodi District of Tianjin from 2011 to 2014 in winter（January, February and December）. The temperature and humidity prediction models in greenhouse by usingstepwise regression and BP neural network were established at 3 periods（0：00-8：00, 8：00-17：00, 17：00-23：00）of 3 kinds of weather types（sunny, cloudy, overcast）. The results showed that：（1） the average accuracy rate ofthe absolute error of simulated and actual values less than 3℃ was 88%, and the root-mean-square error（REMS） was 2℃ under 9 conditions in greenhouse by using stepwise regression model of temperature; theaverage accuracy rate of the absolute error of simulated and actual values less than 3℃ was 94%, and the root-mean-square error（RMES） was 1.6℃ under 9 conditions in greenhouse by using BP neural network model oftemperature; the temperature prediction model established by BP neural network was more accurate and stable;（2） the average accuracy rate of the absolute error of simulated and actual values less than 6% was 81%, and the root-mean-square error（REMS） was 5.7% under 9 conditions in greenhouse by using stepwise regressionmodel of relative humidity; and the average accuracy rate of the absolute error of simulated and actual valuesless than 6% was 80%, and the root-mean-square error（RMES） was 6.7% under 9 conditions in greenhouseby using BP neural network model of relative humidity. Both the 2 models are not suitable for predicting therelative humidity of solar greenhouse at 8：00-17：00, while the humidity prediction model established bystepwise regression at 17：00-23：00 and 0：00-8：00 is more accurate and stable.
作者
温永菁
李春
薛庆禹
董朝阳
黎贞发
李秀芬
陈思宁
Wen Yongjing;Li Chun;Xue Qingyu;Dong Chaoyang;Li Zhenfa;Li Xiufen;Chen Sining(Shenyang Agricultural University,Shenyang 110866;Tianjin Climate Center,Tianjin 300074)
出处
《中国农学通报》
2018年第16期115-125,共11页
Chinese Agricultural Science Bulletin
基金
天津市农业科技成果转化与推广项目"温室小气候资源高效利用及蔬菜茬口搭配技术集成与应用"(201502150)
天津市科委青年基金"日光温室黄瓜霜霉病监测预警技术研究"(16JCQNJC14900)
天津市气象局博士基金"日光温室番茄低温寡照影响评估与风险评价研究"(BSJJ201505)
关键词
日光温室
逐步回归
BP神经网络
温湿度模型
solar greenhouse
stepwise regression
BP neural network
temperature and humidity model
