A method for rapid prediction of the yellowing time of Yuanan yellow tea using artificial neural network with polynomial net structure

Abstract

The method of applying polynomial net structure artificial neural network to quickly predict the yellowing time of Yuanan yellow tea, including: collecting and classifying fresh leaf samples; scanning to obtain near-infrared spectra of fresh leaf samples with different yellowing times; preprocessing the sample spectrum to remove noise After the information is obtained, the sample spectrum is converted into paired data points; then all the spectral data are divided into 20 sub-intervals, and the least squares support vector machine method model of the data of each sub-interval is established respectively, and the best sub-interval for modeling is selected. Interval data; use principal component analysis to extract and compress the best spectral sub-interval information; use the principal component score as the input value, continuously adjust the number of neurons and transfer function, and establish a polynomial net structure artificial neural network prediction model; model robustness test. The rapid, accurate and objective prediction of the yellowing time of yellow tea samples is realized, which can improve the accuracy of predicting the yellowing time and enhance the practicability of the model.

Description

technical field [0001] The invention relates to a method for predicting the yellowing time of yellow tea, in particular to a method for quickly predicting the yellowing time of Yuanan yellow tea by using a polynomial net structure artificial neural network. Background technique [0002] Yellow tea is one of the six major types of tea in my country, and Yuanan yellow tea has the longest history in Hubei Province. Hubei Yuanan has a mild climate, abundant rainfall, and loose and fertile soil. The good ecological environment is very beneficial to the growth of tea trees and ensures the high quality of tea leaves. Therefore, Yuanan Yellow Tea is known as the best tea in Hubei, and it has always been the best-selling tea in the tea market. The tea products are in short supply every year and are deeply loved by everyone. [0003] During processing, the picking standards for fresh leaves of Yuanan yellow tea are generally single bud, one bud and one leaf, and one bud and two leave...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the defects of existing Yuan’an yellow tea, such as manual recording of the vexation time, which cannot accurately grasp the vexation time in real time, and easily lead to a decrease in the quality of the tea, and provide an artificial neural network with a polynomial net structure to quickly predict the vexation of Yuan’an yellow tea. yellow time method

Images