Near-infrared wavelength variable selection method based on continuous projection algorithm

A wavelength variable, projection algorithm technology, applied in the field of analytical chemistry, can solve the problems of high calculation time, low operation efficiency, poor model robustness, etc., to achieve the effect of improving accuracy, reducing dimension and reducing model complexity

Active Publication Date: 2017-08-11
CHONGQING INST OF GREEN & INTELLIGENT TECH CHINESE ACADEMY OF SCI
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above method is difficult to determine the number of sub-intervals, and iterative calculations are required to determine the optimal number of sub-intervals, resulting in high calculation time and low operating efficiency; The subjectivity of the model leads to poor robustness of the model

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 wavelength variable selection method based on continuous projection algorithm
  • Near-infrared wavelength variable selection method based on continuous projection algorithm
  • Near-infrared wavelength variable selection method based on continuous projection algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0030] First, preprocess the near-infrared spectrum to eliminate the noise caused by the signal drift of the instrument itself and environmental changes during the data acquisition process. The commonly used spectral preprocessing methods include SNV (Standard Orthogonal Transformation), OSC (Multiple Scattering Correction), wavelet Transformation, etc.; at the same time, the samples of the calibration set and the prediction set can be divided, such as using the K-S algorithm based on Euclidean distance, the SPXY algorithm considering qualitative variables, etc.

[0031] Realize the flow chart of the present invention as figure 1 As shown, set the following parameters:

[0032] X(n×m): correction set spectrum array,

[0033] α: Threshold floating upper limit ratio, β: Threshold floating lower limit ratio, 0<β<1<α<2,

[0034] h: number of wa...

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 wavelength variable selection method based on a continuous projection algorithm. Using the weight value method, the whole spectrum is divided into three categories: correlated wavenumber point set, irrelevant wavenumber point set, and noise wavenumber point set, and the wavenumber point set is selected from the "correlated wavenumber point set" and "irrelevant wavenumber point set" to establish a calibration model , using orthogonal projection to judge the importance of the newly selected wavelength variable. This method overcomes the linear correlation, effectively reduces the data dimension, extracts the interpretation information to the maximum extent, and ensures the establishment of a correction model with high robustness.

Description

technical field [0001] The invention relates to a near-infrared wavelength variable selection method for analyzing the quality of petroleum or agricultural products, in particular to a near-infrared wavelength variable selection method based on a continuous projection algorithm, and belongs to the technical field of analytical chemistry. Background technique [0002] Near-infrared analysis technology is a rapidly developing high-tech analysis technology in the field of analytical chemistry. It has the advantages of non-destructive, non-polluting, good analysis reproducibility, and low cost. It is widely used in petrochemical, agricultural, food and other industries. For example, in the petrochemical field to measure the octane number of oil products, and in the agricultural field to measure the protein and fat content of grains. However, the near-infrared region (780-2526nm) mainly reflects the combined frequency of hydrogen-containing groups (-OH, -NH, -CH) and the absorpti...

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): G06F19/00
Inventor 刘永福徐泽宇赵健林远长何国田石珍朱晓强吴姣娇
Owner CHONGQING INST OF GREEN & INTELLIGENT TECH CHINESE ACADEMY OF SCI
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