Study on Greenhouse Environment Neural Network Model Based on PSO Algorithm

Abstract

Greenhouse environment models easily fitted strong noise data, and its’ generalization decreased. In this paper, ROLS (Regularized Orthogonal Least Squares) algorithm effectively decreased the influence of noise data, and automatically designed smaller NN structure. PSO (Particle Swarm Optimization) algorithm optimized the parameters of model. Model was experimented with spring environment data of northern greenhouse in China. The results show: compared with model based on OLS algorithm, this model is of smaller NN structure, mean error of temperature and humidity respectively decreases 0.0008 ??? and 0.0004%RH, this model is better on approximation and generalization. The model is beneficial to design control scheme and structure of the northern greenhouse.

Cite this paper

@article{Zhao2010StudyOG, title={Study on Greenhouse Environment Neural Network Model Based on PSO Algorithm}, author={Bin Zhao and Keqi Wang}, journal={2010 International Conference on Intelligent Computing and Cognitive Informatics}, year={2010}, pages={187-190} }