Unlock instant, AI-driven research and patent intelligence for your innovation.

A method based on self-learning to establish fiber type atlas database

A self-learning method and the technology of the graph library are applied in the field of fiber qualitative identification to achieve the effect of expanding the inspection ability

Active Publication Date: 2019-03-12
信融源大数据科技(北京)有限公司 +1
View PDF11 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing fiber type library construction technology is difficult to solve the problem of quickly and efficiently establishing a spectral library covering all fiber types in a short period of time

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
  • A method based on self-learning to establish fiber type atlas database
  • A method based on self-learning to establish fiber type atlas database
  • A method based on self-learning to establish fiber type atlas database

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0090] In the following, the present invention is further described through embodiments with reference to the drawings, but the scope of the present invention is not limited in any way.

[0091] The present invention provides a method for establishing a fiber type map library based on a self-learning method for fiber detection. The same type of detection equipment (such as near-infrared or infrared, Raman spectrometer, etc.) is used to target the same type of fiber map (such as infrared spectroscopy). Map, thermogravimetric map, Raman spectrum), use the sparse autoencoding neural network model to perform feature learning on the fiber map to obtain the fiber feature map, and compare the fiber to be detected with the map in the map library by calculating the similarity Yes, the fiber type of the fiber to be tested can be identified. If the fiber to be inspected is not a known type in the map library, then the fiber is collected in a data set, and when the number of fibers collected...

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 method for establishing a fiber type atlas database based on a self-learning mode, which uses a sparse self-coding neural network model to carry out feature learning on the fiber atlas to obtain a fiber characteristic atlas, thereby establishing a fiber type atlas database. The fiber types of the tested fibers were determined by comparing the similarity and the spectrum in the spectrum library. The invention provides an operable and practical fiber database construction and detection method by using a large-data artificial intelligence method, and solves the problem that the theoretical achievement of identifying fiber types by using a fiber map can be practically applied.

Description

Technical field [0001] The invention relates to the technical field of fiber qualitative identification, in particular to a method for establishing a fiber type map library based on self-learning. Background technique [0002] For the identification of textile fiber types, chemical methods are currently mainly used to qualitatively identify the fibers of the tested samples. The main disadvantage of chemical methods is the pollution of chemicals to the environment and the harm to inspectors. In order to solve the pollution problem of chemical methods, various physical inspection methods have been introduced, such as near-infrared spectroscopy, ultraviolet diffuse reflectance spectroscopy, and Raman spectroscopy. However, in practical applications, when the map of the inspected fiber is obtained, it needs to be compared with the standard map of known fiber types to determine what type of fiber the inspected fiber is. This requires a fiber map library covering all fiber types. At...

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): G06F16/35
Inventor 黄激青范礼阳薛文韬蒋红涛
Owner 信融源大数据科技(北京)有限公司