Development of Granary Temperature and Humidity Prediction Model Based on RBF Neural Network

The traditional prediction methods are generally based on the assumption of linear model. At present, BP neural network and RBF neural network are usually adopted by people in prediction. Since BP neural network has the problem of local optimum and slow training speed, etc., in this paper the method of RBF neural network is adopted in modeling the granary temperature and humidity system, so as to represent the prediction model of granary temperature and humidity system and acquire a recursive prediction model. The experiments results showed that this model can represent the corresponding relationship between the input data vector and the output vector of granary.