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

Determination Method of Sample Components Based on Incremental Partial Least Squares Method

A partial least squares method and partial least squares technology, applied in measuring devices, material analysis through optical means, instruments, etc., can solve the problems of low modeling efficiency, long training time, large space consumption, etc., and achieve prediction error Small size, more modeling time, time and space saving effect

Active Publication Date: 2017-11-14
NORTHEASTERN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The object of the present invention is to provide a sample composition determination method based on incremental partial least squares (Incremental Partial Least Squares, IPLS), which can effectively solve the practical problems that the existing PLS model is used in the online detection of actual production products , especially when using the PLS model for product incremental data detection, it needs to discard the existing model, retrain all the data, and build a new model, which leads to long training time, large space consumption, and low modeling efficiency. When the PLS model predicts the content of ingredients in the sample, the prediction accuracy needs to be further improved

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
  • Determination Method of Sample Components Based on Incremental Partial Least Squares Method
  • Determination Method of Sample Components Based on Incremental Partial Least Squares Method
  • Determination Method of Sample Components Based on Incremental Partial Least Squares Method

Examples

Experimental program
Comparison scheme
Effect test

experiment example 1

[0150] Experimental Example 1: Determination of Compound Chinese Medicines Containing Paeoniflorin

[0151] 1. Purpose of the experiment

[0152] (1) In the decoction of traditional Chinese medicine, a reasonable time can be determined to obtain the original drug with the concentration of paeoniflorin meeting the requirements;

[0153] (2) To verify whether incremental partial least squares (IPLS) is more effective in processing incremental data than traditional partial least squares (PLS).

[0154] 2. Sample prescription and process:

[0155] [Prescription] Bupleurum 180g Yanhusuo (burned) 200g White peony root 240g Roasted licorice 100g

[0156] [Preparation method] The above four flavors are added with water and decocted twice, the first time is 8 times the amount, decocted for 2 hours, and the second time is 6 times the amount and decocted for 1 hour.

[0157] 1. Experiment preparation and sampling rules:

[0158] (1) The experimental equipment and medicinal materials ...

experiment example 2

[0254] Experimental example 2: The effectiveness of the method of the present invention is verified by simulation experiments of grain, soil and grass sample data sets

[0255] 1. Experimental data source

[0256] The grain dataset is provided by Eigenvector Research. The data contains the NIR spectra of 80 grain samples and the corresponding material content (moisture, oil, protein and starch). The spectral collection range is 1100-2498nm, and the collection interval is 2nm.

[0257] In the experiments, the dataset is divided into 60 training samples and 20 testing samples using the Kennard-Stone (KS) method. The training set also uses KS to extract 30 as the initial training set of IPLS1, and 30 as its incremental training set.

[0258] The soil dataset is the absorbance of the organic matter content in the soil sample. Soil samples were obtained from a long-term field experiment in the city of Abisko in northern Sweden. The data contains 108 soil samples, the spectral ...

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 sample composition determination method based on the incremental partial least squares method, comprising the following steps: S1, collecting near-infrared spectral data of the sample to be tested; S2, obtaining the near-infrared spectral data through the incremental partial least squares model The content of each component in the sample corresponding to the spectral data. The present invention processes the near-infrared spectrum data of the sample to be measured by using the incremental partial least squares model, so as to obtain the content of each component in the sample corresponding to the near-infrared spectrum data, which is different from the traditional partial least squares model Compared with data processing, time and space are saved, the obtained regression coefficients are basically the same, but the root mean square error of prediction is smaller. It can be seen that the incremental partial least squares model in the present invention has higher prediction accuracy and modeling efficiency . In addition, the present invention uses a gradient learning method to find optimized regression coefficients, so that the model can be updated more quickly and the ability of the model to adapt to new data can be improved.

Description

technical field [0001] The invention relates to a component determination method, in particular to a sample component determination method based on incremental partial least square method. Background technique [0002] In the production of food, pharmaceuticals and petrochemical products, in accordance with the relevant standards of Process Analysis Technology (PAT) proposed by the American Food and Drug Association, it is necessary to analyze and test the intermediate products in the production process to clarify their substances. Content, state of intermediate products and their changing rules, so as to meet product quality design requirements and produce reliable final products. Near-infrared spectroscopy detection technology has become a general method in process analysis technology due to its fast, non-destructive and low-cost characteristics, and has been widely used in the industry. The principle is: when the near-infrared light irradiates (passes or reflects) the sa...

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
Inventor 赵煜辉王岩单鹏于长永马海涛
Owner NORTHEASTERN UNIV
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