Online prediction method for chemical components in tobacco leaf curing process based on transfer learning and near infrared spectrum

A technology of near-infrared spectroscopy and transfer learning, which is applied in the field of tobacco leaf curing process analysis, can solve problems such as poor prediction results, long cycle time, and high cost, and achieve the effects of improving prediction accuracy, simple operation, and high robustness

Pending Publication Date: 2022-02-25
YUNNAN ACAD OF TOBACCO AGRI SCI
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Due to the influence of environment, climate and other factors, the composition information of tobacco leaves in different years will be different, and the corresponding spectral information will also change accordingly, making the composition detection model based on near-infrared spectroscopy technology in the tobacco leaf curing process no longer applicable. For new samples, if the built model is directly used for the prediction of new tobacco leaf samples, very poor prediction results may be obtained or the model may fail
However, to rebuild an accurate and stable model every year, it is necessary to re-collect samples and measure data. The workload is heavy, the cycle is long, the cost is high, and it does not meet the requirements of actual use.

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
  • Online prediction method for chemical components in tobacco leaf curing process based on transfer learning and near infrared spectrum
  • Online prediction method for chemical components in tobacco leaf curing process based on transfer learning and near infrared spectrum
  • Online prediction method for chemical components in tobacco leaf curing process based on transfer learning and near infrared spectrum

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045] An online prediction method for chemical components in the tobacco leaf curing process based on migration learning and near-infrared spectroscopy, which specifically includes the following steps:

[0046] (1) Collect tobacco leaf samples at predetermined time intervals during the tobacco leaf curing process, collect the spectra of the tobacco leaf samples and determine the chemical composition values, specifically including:

[0047] When collecting the spectrum of tobacco leaves, for each of the tobacco leaf samples, use a fiber optic probe-type near-infrared spectrometer to avoid leaf veins during collection, and measure the spectrum with the fiber optic probe vertically close to the tobacco leaf surface to obtain a stable, smooth and accurate spectrum Information, without destroying the tobacco leaves, convenient and fast;

[0048] Use one of the methods of spectrophotometry, gas chromatography-mass spectrometry, liquid chromatography, continuous flow method, and sol...

specific Embodiment

[0071] An online prediction method for chemical components in the tobacco leaf curing process based on migration learning and near-infrared spectroscopy, which specifically includes the following steps:

[0072] (1) The flue-cured tobacco variety Yunyan 87 was selected, and the pre-cured tobacco leaves were preliminarily screened, and the upper complete and pest-free tobacco leaves with relatively consistent size, shape and maturity were selected for the curing test.

[0073] (2) Collecting samples and measuring near-infrared spectra: Sampling was performed at intervals of 8 hours during the curing process, and 50 tobacco leaf samples were taken each time. Using a fiber optic probe-type near-infrared spectrometer, the fiber optic probe was vertically attached to the tobacco leaf surface to measure the spectrum. The spectral range was set to 900nm-1700nm, the integration time was set to 10ms, and the number of scans was set to 32 times.

[0074] (3) Determination of the water c...

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 belongs to the technical field of tobacco leaf curing process analysis, and particularly relates to an online prediction method for chemical components in the tobacco leaf curing process based on transfer learning and a near infrared spectrum. The method comprises the steps of obtaining a tobacco spectrum in the tobacco leaf curing process; obtaining chemical component values of the tobacco leaves, wherein the chemical component values comprise moisture, starch, protein and total sugar; constructing a prediction model according to the tobacco leaf spectrum and the tobacco leaf curing chemical components; minimizing the difference between a training set tobacco leaf sample and a to-be-predicted feature data set by using a migration component analysis method, and carrying out multiple iterations on the data processed by the migration component analysis method by adopting a partial least square algorithm to train a curing process tobacco leaf chemical component prediction model; and conducting online prediction on the tobacco leaf curing process by using the updated new model, and evaluating a prediction result. The change trend of key chemical components in the tobacco leaf curing process can be predicted, and a basis is provided for accurate adjustment of the tobacco leaf curing process.

Description

technical field [0001] The invention belongs to the technical field of tobacco leaf curing process analysis, in particular to an online prediction method for chemical components in the tobacco leaf curing process based on transfer learning and near-infrared spectroscopy. Background technique [0002] Baking is an important link in determining the final quality of tobacco leaves. The three-stage baking method currently used mainly coordinates the transformation of moisture and substances by controlling the temperature and humidity at different times, so as to achieve the baking goals of yellowing, drying, and aroma. . As a green, non-destructive and rapid process analysis technique, near-infrared spectroscopy can reflect the characteristics of the internal chemical components of tobacco leaves, and has been widely used in the analysis of tobacco leaf curing process. [0003] Due to the influence of environment, climate and other factors, the composition information of tobacc...

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): G01N21/359G06V10/774G06K9/62
CPCG01N21/359G06F18/214
Inventor 邹聪明宾俊张宏孙浩巍徐鸿飞孙建锋陈颐胡彬彬张晓伟张轲姜永雷李贵英汪应华刘羿男鹿晋辉肖毅为
Owner YUNNAN ACAD OF TOBACCO AGRI 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