Unlock instant, AI-driven research and patent intelligence for your innovation.

An optimization method of rice near-infrared spectral model based on spectral ratio subtraction

A near-infrared spectrum and optimization method technology, which is applied in the field of rice near-infrared spectrum model optimization based on spectral ratio deduction, can solve the problems of high difficulty of near-infrared spectrum model analysis and inaccurate prediction, and achieve the effect of improving prediction accuracy

Active Publication Date: 2019-03-19
HEFEI INSTITUTES OF PHYSICAL SCIENCE - CHINESE ACAD OF SCI
View PDF7 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 solve the defects of high difficulty and inaccurate prediction of the near-infrared spectrum model of rice seeds in the prior art, and provide a method for optimizing the near-infrared spectrum model of rice based on spectral ratio deduction to solve the above problems

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
  • An optimization method of rice near-infrared spectral model based on spectral ratio subtraction
  • An optimization method of rice near-infrared spectral model based on spectral ratio subtraction
  • An optimization method of rice near-infrared spectral model based on spectral ratio subtraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] To establish the near-infrared spectrum model of rice seed moisture, the specific steps are as follows:

[0061] Step 1. Construct the rice seed moisture gradient

[0062] In this example, we use this method to analyze the near-infrared spectrum moisture model of 9311 conventional rice population seeds. The modeling set of the average model is: place the rice seeds at four temperatures: normal temperature, 20°C, 30°C, and 40°C. There are 4 humidity values ​​of 11%, 43%, 75%, and 97%, and they are placed for different times to establish corresponding moisture gradients, with a total of 38 points. The construction methods of different temperatures, different times, and different humidity can effectively prevent the non-moisture variables in the model from having the same change trend as the moisture change, which will affect the subsequent analysis of the model.

[0063] The prediction set is the seeds of 9311 seeds placed at 20°C, 25°C, 30°C, 35°C and 11%, 43%, and 75% ...

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 provides a rice near infrared spectrum model optimizing method based on spectrum proportional deduction. The method specifically includes the steps of measuring near infrared spectrums of seeds, seed shells and coarse rice of rice seeds in a near infrared spectrum model multiple times to obtain the near infrared average spectrum of the seeds, seed shells and coarse rice; calculating a fitting spectrum of coarse rice and seed shells and obtaining regression coefficients K1 and K2 according to the formula: the seed average spectrum=K1*rice coarse rice average spectrum+K2*rice seed shell average spectrum; deducting influences of overlapping information according to the values of the coefficients K1 and K2, and establishing an optimized near infrared spectrum model through the fitting spectrum. Compared with the prior art, the influences of inessential redundant information of part of interfering models in the near infrared spectrum model of rice seeds can be removed according to the values of the coefficients K1 and K2 through the fitting spectrum, and therefore the near infrared spectrum model established through the method has better analysis and prediction performance.

Description

technical field [0001] The invention relates to the technical field of near-infrared spectrum model analysis of rice seeds, in particular to a method for optimizing a near-infrared spectrum model of rice based on spectral ratio deduction. Background technique [0002] Paddy rice is a grass plant, and the fruit it bears is paddy rice. It is one of the main food crops in the world and belongs to direct economic crops. Rice as a whole can be divided into two parts: rice husk and brown rice, among which rice is the staple food of the population in East Asia and Southeast Asia, and has more nutrients, including: starch, protein, vitamins, etc. It can also be used in traditional industries such as wine making; rice husk It can be used as feed, etc. Near-infrared (NIR) spectroscopy is the absorption spectrum of a substance at a wavelength of 780-2526nm. It has been widely used in agriculture because of its non-destructive, fast, multi-component, and non-polluting analysis characte...

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): G01N21/359G01N21/3563G01N21/3554
CPCG01N21/3554G01N21/3563G01N21/359
Inventor 黄青王纯阳
Owner HEFEI INSTITUTES OF PHYSICAL SCIENCE - CHINESE ACAD OF SCI