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

Near infrared spectrum quantitative model simplification method based on principal component analysis

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

Active Publication Date: 2014-11-26
CHINA TOBACCO YUNNAN IND
View PDF5 Cites 19 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
  • Near infrared spectrum quantitative model simplification method based on principal component analysis
  • Near infrared spectrum quantitative model simplification method based on principal component analysis
  • Near infrared spectrum quantitative model simplification method 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] Image 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 near infrared spectrum quantitative model simplification method based on principal component analysis. The method comprises the following steps: preprocessing a collected near infrared spectrum, and dividing the spectrum and corresponding to-be-detected component concentration data into a training set, a detection set and a prediction set; simultaneously combining a processed spectrum matrix and a to-be-detected component concentration matrix to form a simultaneous matrix, and decomposing principal components to obtain each wavelength variable and load of the to-be-detected component; calculating an included angle between each wavelength variable and the load of the to-be-detected component concentration; reserving the wavelength variable with the angular value meeting an optimal angular value; establishing an optimal model by utilizing the reserved wavelength variable, and predicting the to-be-detected component concentration of a sample of the prediction set. By adopting the method, the wavelength variable containing the concentration information can be accurately extracted, the quantitative analysis model can be maximally simplified while the precision is guaranteed, and a novel quantitative model simplification method is provided for the near infrared spectrum multivariate correction and analysis.

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
IPC IPC(8): G01N21/359
CPCG01N2201/129G01N21/359
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