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

Fast determining method for grade of machine-pick fresh leaves Eyebrow tea polishing samples based on particle swarm optimization algorithm

A technology of particle swarm optimization and judgment method, which is applied in the level field, can solve problems such as strong subjectivity and error-prone, and achieve the effects of reducing the amount of model calculation, objective prediction, and simplifying the model structure

Inactive Publication Date: 2019-10-11
INST OF FRUIT & TEA HUBEI ACAD OF AGRI SCI
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method based on the particle swarm optimization algorithm for the defects of strong subjectivity and error-proneness in the current refined eyebrow tea tea processing personnel who usually rely on their own work experience and sensory organs to determine the grade of fresh leaf eyebrow tea car color samples. A rapid determination method for the grade of machine-harvested fresh leaf eyebrow tea color samples

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
  • Fast determining method for grade of machine-pick fresh leaves Eyebrow tea polishing samples based on particle swarm optimization algorithm
  • Fast determining method for grade of machine-pick fresh leaves Eyebrow tea polishing samples based on particle swarm optimization algorithm
  • Fast determining method for grade of machine-pick fresh leaves Eyebrow tea polishing samples based on particle swarm optimization algorithm

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0083] (1) Sample collection and classification

[0084] Collected 120 machine-harvested fresh leaf eyebrow tea color samples from Hubei Province, divided into 3 different grades: 7-8 mesh grade samples, 9-10 mesh grade samples and 11-16 mesh grade samples. According to the different sample grades, the samples were divided into two sets according to the ratio of 3:1, a calibration set and a validation set, of which 90 samples were in the calibration set and 30 samples in the validation set were used to test the robustness of the calibration set model. Among them, the chemical value of the 7-8 mesh grade sample is set to 1.000, the chemical value of the 9-10 mesh grade sample is set to 2.000, and the chemical value of the 11-16 mesh grade sample is set to 3.000.

[0085] (2) Spectrum scanning

[0086] The near-infrared spectrum of all three grades of car color samples is obtained by using the Antaris II Fourier transform near-infrared spectrometer (FT-NIR) of the American Ther...

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 present invention discloses a fast determining method for grade of machine-pick fresh leaves Eyebrow tea polishing samples based on the particle swarm optimization algorithm. The method comprises:collecting and classifying samples: scanning to obtain near-infrared spectrum of different grades of eyebrow tea polishing samples; pre-processing the sample spectrum to remove noise information, andthen converting the sample spectrum into pairs of data points; dividing all spectrum data into 20 sub-intervals, respectively establishing a particle swarm optimization algorithm model of each sub-interval data, and screening out best sub-interval data of the modeling; applying a principal component analysis method to extract and to compress optimal spectrum sub-interval information; using a principal component score as an input value, continuously adjusting the number of neurons and a transfer function, and establishing an unsupervised Kohonen structure artificial neural network prediction model; and testing model robustness. The method realizes fast, accurate and objective prediction of the Hubei Eyebrow tea polishing samples, and improves accuracy of predicting the grade of the Hubei eyebrow tea polishing samples and enhances practicability of the model.

Description

technical field [0001] The present invention relates to a method for judging the grade of tea-eyebrow tea color samples, and more specifically to a method for quickly judging the grade of tea-eyebrow tea color samples collected by machine based on a particle swarm optimization algorithm. Background technique [0002] Eyebrow tea is one of the treasures of green tea; Hubei eyebrow tea is a major export tea product in my country, and is deeply loved by foreign customers. There are trade standard samples for its quality. Usually, the refining process of eyebrow tea is as follows: ① Primary green tea ② Re-rolling ③ Sieving ④ Shaking ⑤ Machine inspection ⑥ Refining fan ⑦ Electric picking ⑧ Car color ⑨ Tight door ⑩ Heap evenly, among which car color is the most important part of eyebrow tea refining The key process, the color of the car, is related to the tight knot and straightness of the rope, and the green and frosty color, thus forming the unique quality of eyebrow tea. [00...

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
IPC IPC(8): G01N21/359G06N3/00G06N3/04
CPCG01N21/359G01N2021/3595G06N3/006G06N3/04
Inventor 龚自明王胜鹏高士伟叶飞桂安辉郑鹏程滕靖王雪萍郑琳刘盼盼
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