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

Non-destructive prediction method of Yuan'an yellow tea boredom time based on least squares support vector machine

A technology of support vector machine and least squares, applied in the direction of measuring devices, instruments, biological neural network models, etc., can solve the problems of tea quality degradation and the inability to accurately grasp the time of dryness in real time, and achieve objective and accurate prediction of sample dryness Yellow time, effect of increasing robustness

Active Publication Date: 2022-05-06
INST OF FRUIT & TEA HUBEI ACAD OF AGRI SCI
View PDF19 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the defects of the existing Yuanan yellow tea, such as manual recording of the dull yellowing time, which cannot accurately grasp the dull yellowing time in real time, and easily lead to a decrease in the quality of the tea, and provide Yuanan yellow tea dull yellow tea based on the least squares support vector machine. A Lossless Prediction Method of Time

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
  • Non-destructive prediction method of Yuan'an yellow tea boredom time based on least squares support vector machine
  • Non-destructive prediction method of Yuan'an yellow tea boredom time based on least squares support vector machine
  • Non-destructive prediction method of Yuan'an yellow tea boredom time based on least squares support vector machine

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0082] (1) Fresh leaf sample collection and classification

[0083] Collect single bud (stemless), one bud and one leaf (consisting of single bud, first leaf and longer stem) and one bud and two leaves (consisting of single bud, first leaf, second leaf) of Anji white tea varieties in Yuan'an County, Hubei Province and long stalks) 120 samples of fresh leaves from three different parts. After the sample is finished, the yellowing is carried out, and the yellowing time is accurately recorded at the same time. According to the different yellowing time, the samples were divided into two sets of calibration set and verification set according to the ratio of 3:1, of which 90 samples were in the calibration set and 30 samples in the verification set were used to test the robustness of the calibration set model.

[0084] (2) Spectrum scanning

[0085] Using Thermo Fisher Scientific Antaris II Fourier transform near-infrared spectrometer (FT-NIR) and an integrating sphere diffuse ref...

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 non-destructive prediction method of the yellowing time of Yuanan yellow tea based on the least squares support vector machine, including: collection and classification of fresh leaf samples; scanning to obtain the near-infrared spectra of fresh leaf samples with different yellowing time; preprocessing and eliminating the sample spectrum After the noise information, the sample spectrum is converted into pairs of data points; then all the spectral data are divided into 20 sub-intervals, and the least squares support vector machine method model of each sub-interval data is established to screen out the best model. Subinterval data; use principal component analysis to extract and compress the best spectral subinterval information; use the principal component score as the input value, continuously adjust the number of neurons and transfer function, and establish a general regression structure artificial neural network prediction model; the model is robust sex test. The rapid, accurate and objective prediction of the yellowing time of the yellow tea samples is realized, and the purpose of improving the accuracy of predicting the yellowing time and enhancing the practicability of the model is achieved.

Description

technical field [0001] The invention relates to a method for predicting the time of dull yellow tea, and more specifically relates to a nondestructive prediction method for the time of dull yellow tea of ​​Yuan'an yellow tea based on a least squares support vector machine. Background technique [0002] Yellow tea is one of the six major teas in my country, and Yuan'an yellow tea has the longest history in Hubei Province. Hubei Yuan'an has a mild climate, abundant rainfall, loose and fertile soil, and a good ecological environment is very beneficial to the growth of tea trees, which ensures the high quality of tea. Therefore, Yuan'an Yellow Tea is known as the best tea in Hubei, and it has always been a relatively popular 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 ...

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 Patents(China)
IPC IPC(8): G01N21/359G06N3/02
CPCG01N21/359G06N3/02G01N2021/3595
Inventor 王胜鹏龚自明高士伟郑鹏程滕靖叶飞王雪萍郑琳刘盼盼
Owner INST OF FRUIT & TEA HUBEI ACAD OF AGRI SCI
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