A method for quantitative analysis of substance content

A quantitative analysis and material content technology, applied in color/spectral characteristic measurement, complex mathematical operations, etc., can solve problems such as slow learning speed, large quantitative analysis error, and large load, and achieve high-precision results

Inactive Publication Date: 2020-07-28
WUHAN POLYTECHNIC UNIVERSITY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, if there are abnormal samples in the training samples, the partial least squares regression model will become unstable due to the influence of abnormal samples, and the quantitative analysis error will be large
[0006] The Chinese patent application number is CN201510407751.X. This invention provides a quantitative analysis of complex samples. Due to the problems of large load, slow learning speed, and easy to fall into local minima in traditional modeling methods, this invention introduces non- A linear extreme learning machine (ELM) to establish a quantitative analysis method for complex 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
  • A method for quantitative analysis of substance content
  • A method for quantitative analysis of substance content
  • A method for quantitative analysis of substance content

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0064] Such as figure 1 As shown in the flow diagram of the first embodiment:

[0065] A method for quantitative analysis of substance content, comprising the following steps:

[0066] S100: reading the spectrum of the measured substance;

[0067] S200: setting the spectrum matrix and response matrix of the measured substance;

[0068] S300: Establish a mathematical model according to the spectral matrix and the response matrix;

[0069] S400: Solve the direction vector of the mathematical model;

[0070] S500: Repeat steps S200 to S400 to obtain several direction vectors

[0071] S600: Perform conversion according to several direction vectors to obtain a prediction function.

[0072] Preferably, in the method for quantitative analysis of substance content, the instrument for quantitative analysis of substance content is a spectrometer, gas chromatography-mass spectrometer, liquid chromatography-mass spectrometer or nuclear magnetic resonance spectrometer.

[0073] Prefe...

no. 3 example

[0127] Based on the above analysis method, the results of the second specific experimental analysis and comparison are as follows:

[0128] 1. Spectral analysis of marzipan, the spectral data set consists of 32 data, and the analysis indicators are moisture and sugar. Randomly select 60% of the samples as training samples and the rest as testing samples. At the same time, random noise is added to the first five training samples, such as figure 2 It is a schematic diagram showing the water content analysis results of almond syrup in the third embodiment of the present invention.

[0129] The ordinate represents the error, and the abscissa represents the number of w. □ represents the partial least squares analysis error, △ represents the analysis error of the method of the present invention, ○ represents the partial least squares analysis error of orthogonal signal correction, and ◇ represents the principal component regression analysis error of 1 norm.

[0130] 2. Pork spec...

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 quantitative analysis method for substance content. The technical field related to the quantitative analysis method of substance composition and content, specifically a quantitative analysis method of substance content, including the following steps: S100: read the spectrum of the substance to be measured; S200: set the spectrum matrix and response of the substance to be measured Matrix; S300: Establish a mathematical model according to the spectral matrix and the response matrix; S400: Solve the direction vector of the mathematical model; S500: Repeat steps S200 to S400 to obtain several direction vectors; S600: According to several The direction vector is converted to obtain the prediction function.

Description

technical field [0001] The invention relates to the technical field of quantitative analysis methods for material components and contents, in particular to a method for robustly establishing an analysis model. Background technique [0002] Quantitative analysis of substances is an important means to study the properties of substances. Regression is a commonly used quantitative model modeling method. Assuming that the spectral matrix is ​​X∈n×p, which is a matrix with n rows and p columns, and the response matrix is ​​Y∈n×q, which is a matrix with n rows and q columns, the ordinary least squares regression is to find the regression coefficient w to satisfy: [0003] [0004] Where||·|| F Indicates to find the F norm, and it is easy to get w=(X T X) -1 XY. However, usually the number n of infrared spectra is smaller than the dimension p of the spectrum, so there is a high degree of correlation between variables such that X T X is not reversible, so the ordinary least ...

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): G01N21/25G06F17/18
CPCG01N21/25G06F17/18
Inventor 牟怿周龙陈为真黄海林范吉军卢亚玲
Owner WUHAN POLYTECHNIC UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap