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

A simplification method of near-infrared spectroscopy quantitative model based on principal component analysis

A near-infrared spectroscopy and principal component analysis technology, applied in the field of near-infrared spectroscopy quantitative model simplification based on principal component analysis technology, can solve the problems of model overfitting, easy to fall into local optimum, long calculation cycle of genetic algorithm, etc. Reliable results, high practical value, accurate extraction effect

Active Publication Date: 2016-11-30
CHINA TOBACCO YUNNAN IND
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods still have their own shortcomings. For example, the genetic algorithm (GA) has a long calculation cycle and is easy to fall into the local optimum; the leave-one-out cross-validation method is used in the uninformative variable elimination method (UVE), which makes the model overfitting. joint risk

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 simplification method of near-infrared spectroscopy quantitative model based on principal component analysis
  • A simplification method of near-infrared spectroscopy quantitative model based on principal component analysis
  • A simplification method of near-infrared spectroscopy quantitative model based on principal component analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] The content of total sugar components in tobacco samples was determined by near-infrared spectroscopic analysis. The specific steps are as follows:

[0029] 1) A quantitative analysis model was established by measuring the near-infrared spectra of 1003 tobacco samples. The spectra were measured by an MPA FT-NIR spectrometer (Bruker, Germany), with a wavenumber range of 3999.8-11996 cm -1 (2500.2-833.7nm), the sampling interval is about 4 wavenumbers, a total of 2074 wavelength variables. Adopt AAIII type continuous flow analyzer (BRAN+LUBBE, Germany) to determine the content of total sugar in the sample according to the standard method;

[0030] 2) Use continuous wavelet transform (Haar wavelet, scale factor 20) to preprocess the collected sample spectrum to subtract the influence of background drift. Use the KS algorithm to divide the preprocessed sample spectrum into three parts: training set, test set and prediction set. The number of samples in the training set is...

Embodiment 2

[0039] The content of nicotine components in tobacco samples was determined by near-infrared spectroscopic analysis. The specific steps are as follows:

[0040] 1) A quantitative analysis model was established by measuring the near-infrared spectra of 1003 tobacco samples, and the spectra used Antaris TM Measured by II FT-NIR spectrometer (Thermo Electron Corporation, USA), the wavenumber range is 4000-10000cm -1 (2500-1000nm), the sampling interval is about 4 wavenumbers, a total of 1557 wavelength variables. Adopt AAIII type continuous flow analyzer (BRAN+LUBBE, Germany) to measure the content of nicotine in the sample according to standard method;

[0041] 2) Use continuous wavelet transform (Haar wavelet, scale factor 20) to preprocess the collected sample spectrum to subtract the influence of background drift. Use the KS algorithm to divide the preprocessed sample spectrum into three parts: training set, test set and prediction set. The number of samples in the traini...

Embodiment 3

[0050] The content of total nitrogen in tobacco samples was determined by near-infrared spectroscopic analysis. Establish a quantitative analysis model by measuring the near-infrared spectra of 1003 tobacco samples, using Antaris TM Measured by II FT-NIR spectrometer (Thermo Electron Corporation, USA), the wavenumber range is 4000-10000cm -1 (2500-1000nm), the sampling interval is about 4 wavenumbers, a total of 1557 wavelength variables. AAIII type continuous flow analyzer (BRAN+LUBBE, Germany) was used to determine the content of total nitrogen in the samples according to the standard method. The implementation steps are basically the same as those in Examples 1 and 2, wherein the number of model factors of the partial least squares regression is 12.

[0051] Figure 6 It is the load distribution diagram of the near-infrared spectrum wavelength variable, the selected wavelength variable and the total sugar component of the tobacco sample on the 1 and 2 principal component...

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 discloses a method for simplifying a near-infrared spectrum quantitative model based on principal component analysis. After preprocessing the collected near-infrared spectrum, divide the spectrum and the corresponding concentration data of the components to be measured into a training set, a detection set and a prediction set; combine the processed spectral matrix and the concentration matrix of the components to be measured to form a simultaneous matrix , and perform principal component decomposition to obtain the load of each wavelength variable and the component to be measured; calculate the angle between each wavelength variable and the concentration load of the component to be measured; the wavelength variable whose angle value satisfies the optimal angle value is retained ; Use the retained wavelength variable to establish an optimal model to predict the concentration of the component to be measured in the prediction set sample. This method can accurately extract the wavelength variable containing concentration information, and simplify the quantitative analysis model to the greatest extent while ensuring the accuracy.

Description

technical field [0001] The invention belongs to the technical field of near-infrared spectrum non-destructive analysis, and in particular relates to a method for simplifying a near-infrared spectrum quantitative model based on principal component analysis technology. Background technique [0002] Near-infrared spectroscopy (NIR) non-destructive analysis technology has the advantages of simple sample processing, fast analysis speed, environmental friendliness, easy on-line analysis, good stability, etc., and has been widely used in agriculture, petrochemical, medical, pharmaceutical, food, tobacco, life Science, environmental protection and other industries. However, the near-infrared spectrum of complex samples has many absorption peaks, serious overlapping, and complex bands; in addition to its own information, it often contains a lot of noise and background information; it is easily affected by measurement conditions (such as temperature, instrument), sample state (such as...

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): G01N21/359
Inventor 王家俊徐广晋者为李庆华冯洪涛段焰青曾晓鹰陈剑明胡巍耀周桂园
Owner CHINA TOBACCO YUNNAN IND
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com