Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Soil humidity prediction method for optimizing BP neural network based on improved genetic algorithm

A technology of BP neural network and improved genetic algorithm, applied in neural learning methods, biological neural network models, genetic rules, etc., can solve problems such as large errors in BP neural network, achieve accurate prediction, avoid local optimum, and agricultural production technology Improved effect

Pending Publication Date: 2021-08-06
HEILONGJIANG UNIV +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention is used to solve the problem of soil moisture prediction. Since the error of a single BP neural network is large when predicting, a soil moisture prediction method based on an improved genetic algorithm is proposed to optimize the BP neural network.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Soil humidity prediction method for optimizing BP neural network based on improved genetic algorithm
  • Soil humidity prediction method for optimizing BP neural network based on improved genetic algorithm
  • Soil humidity prediction method for optimizing BP neural network based on improved genetic algorithm

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0017] Step 1: Enter data, divide the collected data into two groups, one set as training data, and another as test data.

[0018] Step 2: Determine the topology of the neural network, setting the parameters of the neural network including the number of input layers, implicit layers, and output layer neurons.

[0019] Step 3: Initialize the BP neural network and obtain the initial weight and threshold of the neural network.

[0020] Step 4: Initialize the genetic algorithm and encodes the initial weights and thresholds.

[0021] Step 5: Set the adaptation function of the genetic algorithm, the error square root of the BP neural network training as the adaptive function value.

[0022] Step 6: Select, cross, and variation operations.

[0023] Step 7: Calculate the adaptivity value, determine if the termination condition is met, if the termination condition is satisfied, then the optimal weight value and threshold is determined, and if the termination condition is not met, step 6 is...

example 2

[0037] Test theoretical analysis.

[0038] The BP Neural Network Algorithm is a typical multi-layer feedforward neural network that conducts learning training through the error reverse propagation algorithm. The operation characteristics of this neural network are data forward communication, and the error reverse propagation. The BP neural network mainly includes input layers, implicit layers, and output layers. During training, neural networks continue to adjust the input layer and the implicit layer and the weight and threshold between the implicit layer and the output layer, when the neural network output value Training is stopped with the target value, which has a good generalization ability.

[0039] The calculation formula of the BP neural network is as follows.

[0040] .

[0041] The working process of the BP neural network is to subtilize the input data from the input layer to the hidden layer, and then map the threshold to the threshold, and then map the hidden layer o...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a soil humidity prediction method based on an improved genetic algorithm optimized BP neural network. The method comprises the following steps of: 1, inputting data, dividing the collected data into two groups, taking one group as training data, and taking the other group as test data; 2, determining a topological structure of the neural network, and setting various parameters of the neural network, including the number of neurons of an input layer, a hidden layer and an output layer; 3, initializing the BP neural network, and obtaining an initial weight and a threshold value of the neural network; 4, initializing a genetic algorithm, and encoding an initial weight and a threshold value; 5, setting a fitness function of the genetic algorithm; 6, performing selection, crossover and mutation operations; 7, calculating a fitness value, and judging whether a termination condition is met or not; and 8, determining to obtain an optimal weight and an optimal threshold, and completing the prediction of the soil humidity. The method is used for solving the problems that when a pure BP neural network model is used for predicting the soil humidity, errors are large, and soil humidity prediction is not accurate.

Description

Technical field [0001] The present invention belongs to the field of soil humidity prediction techniques, and more particularly to a soil humidity prediction method based on improved genetic algorithm optimizing BP neural network. Background technique [0002] With the continuous development of sensor technology, it is born with intelligent agricultural operations of crop growth information to achieve farmers. Smart agriculture mainly collects environmental parameters in crop production through sensors, and then transmits data to the network terminal via the Internet, and finally analyzes data to develop a reasonable crop production plan. Among the data of the production environment monitoring of crop production environment, the prediction of soil humidity and its important, the dry wetness of the soil is related to the production of crops, and only reasonable soil humidity can make the crops grow normally. [0003] At present, the measurement of soil humidity is mainly relying o...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/27G06Q10/04G06Q50/02G06N3/08G06N3/12G06F111/08
CPCG06N3/084G06N3/126G06Q10/04G06Q50/02G06F30/27G06F2111/08
Inventor 刘勇王佳楠时龙闽何淑林刘士琛
Owner HEILONGJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com