Genetic BP neural network-based solar greenhouse temperature prediction method

Abstract

The invention discloses a genetic BP neural network-based solar greenhouse temperature prediction method. According to the method, on the basis of analysis on main factors affecting the microclimate environment of a greenhouse, with the temperature and light in the greenhouse and the difference of temperature inside and outside the greenhouse adopted as model input, a BP neural network-based greenhouse temperature prediction model is constructed; and the BP neural network algorithm is improved by using the genetic algorithm to optimize the weight and threshold of the network, and therefore, agenetic BP neural network-based greenhouse temperature prediction model is constructed. A simulation result shows that the prediction effect of the genetic algorithm optimized BP neural network has fewer errors and higher prediction than the prediction effect of the BP neural network, and can realize effective prediction of the temperature of the solar greenhouse.

Description

technical field [0001] The invention relates to a method for predicting the temperature of a solar greenhouse, in particular to a method for predicting the temperature of a solar greenhouse based on a genetic BP neural network. Background technique [0002] Facility horticulture is an environment-controlled industry that improves the local environment through modern agricultural engineering, mechanical technology and management technology, and can provide crops with microclimate environments such as temperature, light, water, gas, and fertilizer that are suitable for their growth. my country's protected vegetable cultivation area accounts for more than 90% of the world's total area, and has become an important part of my country's modern agriculture. The solar greenhouse is the main body of facility production. It relies on the natural heating of sunlight during the day and the heat preservation equipment at night to create the required indoor temperature. It can produce off...

AI Technical Summary

Problems solved by technology

Li Yongbo et al. proposed the uniformity control of greenhouse temperature field and the multi-index GA optimization control method based on the CFD steady-state simulation model. Qu Yi et al. combined the radial basis function neural network and the PID control law to form a neural network RBF-PID controller to realize Greenhouse temperature control, Zuo Zhiyu et al. proposed to use the time series analysis method to establish a temperature prediction model, but only considered a single factor affecting indoor temperature

Images