Air humidity prediction system in greenhouse strawberries based on CPSO-BP neural network

Abstract

The invention discloses an air humidity prediction system in greenhouse strawberries based on a CPSO-BP neural network, and the system comprises a reset circuit which employs an external RST pin resetmode; a clock circuit, provided with a control chip for recording completion time, and a 31-byte static RAM being attached to the clock circuit; a communication circuit, composed of three parts, namely an electric part, a charge pump circuit and a data conversion channel; a storage circuit, provided with a data storage end for storing air humidity detected at different time, and is packaged by adopting a DIP8 pin; a power circuit, provided with a transformer and a bridge rectifier circuit, the input end of the transformer being connected with the power plug through a fuse, and the output endof the transformer being connected to the bridge rectifier circuit composed of four diodes; a humidity detection circuit, provided with a detection end for detecting air humidity and a data acquisition end electrically connected with the detection end. According to the system, the accuracy of a BP neural network algorithm can be effectively improved, and the air humidity in greenhouse strawberriescan be more effectively controlled.

Description

technical field [0001] The invention belongs to the field of intelligent agriculture, in particular to an air humidity prediction system based on CPSO-BP neural network in greenhouse strawberries. Background technique [0002] During the growth of crops, crops have different requirements for air humidity in different growth periods. Humidity has a serious impact on the growth of crops. The yield of crops is closely related to its growth humidity, especially strawberries. The requirements are high; currently, the circuit board is controlled by the BP neural network algorithm to control the humidity; [0003] The traditional BP neural network generally refers to a multi-layer feed-forward neural network trained by the error backpropagation (BackPropagation, BP) algorithm. Its nonlinear mapping ability is weak, and traditional algorithms such as BP neural network have low detection accuracy and cannot Accurate detection of humidity. Contents of the invention [0004] In som...

AI Technical Summary

Problems solved by technology

[0003] The traditional BP neural network generally refers to a multi-layer feed-forward neural network trained by the error backpropagation (BackPropagation, BP) algorithm. Its nonlinear mapping ability is weak, and traditional algorithms such as BP neural network have low detection accuracy and cannot Accurate detection of humidity

Images