基于遗传算法优化模糊神经网络的温室温度预测模型  

Greenhouse Temperature Prediction Model Based on Genetic Algorithm Optimized Fuzzy Neural Network

作　　者：张龙 贾兰芳[1] ZHANG Long;JIA Lan-fang(Department of Electronic Information and Physics,Changzhi University,Changzhi Shanxi,046011)

机构地区：[1]长治学院电子信息与物理系,山西长治046011

出　　处：《山西大同大学学报（自然科学版）》2021年第3期15-17,共3页Journal of Shanxi Datong University(Natural Science Edition)

摘　　要：在农业生产发展当中,影响温室农作物产量的因素有很多,温度是最重要的环境参数之一,与其他各环境因素具有很高的耦合度,存在非线性问题。针对上述问题本文提出了一种基于遗传算法优化模糊神经网络(GA-FNN)的温室温度预测模型。在温室内选取湿度、CO_(2)、大气压和光照强度数据作为模型输入,温度数据作为模型唯一输出。试验结果表明,获得最佳隐含层节点数为4、隶属度函数参数(C_(ji),b_(i))参数分别为2.9203和2.2588,RMSE,MAE,MAPE分别提升了51.3%、54.2%、17.1%。In the development of agricultural production,there are many factors that affect the yield of greenhouse crops.Temperature is one of the most important environmental parameters.It has a high degree of coupling with other environmental factors and has nonlinear problems.In view of the above problems,this paper proposes a greenhouse temperature prediction model based on genetic algorithm optimized fuzzy neural network(GA-FNN).In the greenhouse,humidity,CO_(2),atmospheric pressure and light intensity data are selected as the model input,and temperature data is the only output of the model.The test results show that the optimal number of hidden layer nodes is 4,the membership function parameters(C_(ji),b_(i))parameters are 2.9203 and 2.2588,RMSE,MAE,and MAPE have increased by 51.3%,54.2%,17.1%.

关 键 词：遗传算法 模糊神经网络、温室温度、预测模型 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] S625[自动化与计算机技术—控制科学与工程]