Model transfer method based on spectral data

A technology of spectral data and transfer method, applied in the field of infrared spectral analysis, which can solve the problems of poor transfer effect, complex adjustment of window size, local noise effect, etc.

Active Publication Date: 2019-03-08
SHANDONG UNIV
View PDF6 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method is more complicated to adjust the window size and cannot be self-adaptive. If the window size parameter is not set properly, the transfer effect will not be good, and local noise will also have a certain impact

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
  • Model transfer method based on spectral data
  • Model transfer method based on spectral data
  • Model transfer method based on spectral data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0081] Example 1: Comparison with a Chinese invention patent CN105842190A based on a spectral regression-based near-infrared model transfer method;

[0082] 1. Theoretical analysis:

[0083] The general model transfer method uses high-quality (high-resolution, high-precision) spectra to correct the target spectrum. According to the principle described in the patent (CN105842190A), the host near-infrared spectrum X m and slave NIR X s is through their corresponding low-dimensional representation Z m and Z s Using the transformation matrix F 1 linked together. where Z m =A m T x m , A m is the projection vector set of the host, it can be seen that Z m is x m Obtained after a certain transformation. Since under the h eigenvectors, the normalized least squares method is used to solve the projection vector, and then A m , therefore, Z m is for X under h eigenvectors m Approximate representation of , that is, after Z m =A m T x m After Z m Relative X m There is ...

Embodiment 2

[0091] Example 2 Model Forward Transfer

[0092] Take the determination of the content of astragaloside IV in the commercially available Radix Astragalus extract as an example. The content of astragaloside IV was determined by HPLC liquid chromatography, and the specific method was described in Chinese Pharmacopoeia (2015 edition).

[0093] I. Sample index determination and spectrum collection

[0094] A total of 82 samples of commercially available Astragalus extracts were collected, and the content of astragaloside IV was determined with reference to the pharmacopoeia method (2015 edition). The main instrument (Thermo Fisher Scientific, USA) and the target instrument (Viavi 1700, USA) were used to measure the nearly Infrared Spectrum, X M Indicates the near-infrared spectrum measured by the main instrument, X T Indicates the near-infrared spectrum measured by the target instrument. The near-infrared spectra measured by the main instrument and the target instrument are as...

Embodiment 3

[0109] Example 3 Model reverse transfer

[0110] Transfer the main instrument to collect sample near-infrared spectrum data (denoted as X Mt ) through the formula X Mt = S Mt V Mt ’ Decompose the principal components and determine the appropriate number of principal components l M . Its determination method is consistent with the above-mentioned embodiment 2. The selection method of the transfer set is also consistent with that in Embodiment 2.

[0111] X of the target instrument Tt with S Mt Press S Mt =X Tt f Tt associated. where F Tt The calculation of can be solved by the partial least squares method, and the corresponding number of latent factors can be determined by the leave-one-out method. Try different numbers of transfer set samples, and select and determine the transfer set samples according to the principle of minimum RMSEP value. After the transfer set samples are determined, F Tt It is also determined by this. Since the unknown sample is predicted...

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 embodiment of the application discloses a model transfer method based on spectral data. The method includes measuring indexes of samples and collecting spectra; pretreating the spectra; dividing aplurality of the calibration samples into correction samples and prediction samples; preforming model transfer from a main instrument to a target instrument, namely, forward transfer; and alternatively, performing model transfer from the target instrument to the main instrument, namely, backward transfer. Compared with the traditional method, the method has the following advantages that: the interference of noise and irrelevant information can be suppressed through the correlation between the collected spectral data of the samples and the spectral data structure; two-way model transfer of themain instrument and the target instrument can be realized, and whether the instrument types of the main instrument and the target instrument are consistent or not is unrestricted, and whether collected spectral data points are consistent or not is unrestricted, so that the method is of great significance for model sharing of different types of spectrometers with the same spectral method and improving the applicability of the model.

Description

technical field [0001] The embodiment of the present application relates to the technical field of infrared spectral analysis, in particular to a model transfer method based on spectral data. Background technique [0002] Modern spectral analysis technology is a comprehensive analysis technology that intersects multiple disciplines (spectral detection, chemometrics, computer science and statistics, etc.). Spectral analysis technology is widely used in petrochemical, agricultural, food and pharmaceutical fields. The use of spectroscopic analysis for the determination of material composition and online process analysis requires the establishment of a multivariate calibration model, that is, the use of standard methods to measure the indicators of calibration samples (such as component content or activity values ​​or other physical and chemical indicators, etc.), and then use spectrometers to measure these samples. The spectrum of the unknown sample is established by associati...

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 Applications(China)
IPC IPC(8): G01N21/35G01N21/359
CPCG01N21/35G01N21/359
Inventor 聂磊苏美臧恒昌周军纪立顺田进国姜文文刘肖雁孙越
Owner SHANDONG UNIV
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