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

A Method of Establishing Fiber Species Atlas Library Based on Self-learning

A self-learning method and a technology of atlas library, applied in the field of fiber qualitative identification

Inactive Publication Date: 2021-09-24
信融源大数据科技(北京)有限公司 +1
View PDF11 Cites 0 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 of Establishing Fiber Species Atlas Library Based on Self-learning
  • A Method of Establishing Fiber Species Atlas Library Based on Self-learning
  • A Method of Establishing Fiber Species Atlas Library Based on Self-learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0090] Below in conjunction with accompanying drawing, further describe the present invention through embodiment, but do not limit the scope of the present invention in any way.

[0091] The invention provides a method for fiber detection based on a self-learning method to establish a fiber type atlas library, using the same type of detection equipment (such as near-infrared or infrared, Raman spectrometer, etc.), for the same type of fiber atlas (such as infrared spectrum graph, thermogravimetric map, Raman spectrogram), use the sparse self-encoder neural network model to learn the features of the fiber map, obtain the fiber feature map, and compare the fiber to be detected with the map in the map library by calculating the similarity Yes, thus identify the fiber type of the fiber to be detected. If the fiber to be detected is not a known type in the atlas library, then the fiber is collected in a data set, and when the number of fibers collected in the data set reaches a cer...

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 library based on a self-learning method, using a sparse self-encoding neural network model to perform feature learning on fiber atlases to obtain a fiber feature atlas, thereby establishing a fiber type atlas library; and A certain degree of similarity is compared with the spectrum in the spectrum library to determine the fiber type of the fiber to be tested. The present invention provides an operable and practical fiber database building and detection method by using the artificial intelligence method of big data, and solves the problem that the theoretical achievements of using fiber atlas to identify fiber types 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 atlas library based on self-learning. Background technique [0002] For the identification of textile fiber types, chemical methods are mainly used to qualitatively identify the fibers of the samples under inspection. The main defect of the chemical method is that the chemicals pollute the environment and harm the 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, after obtaining the pattern of the inspected fiber, it needs to be compared with the known standard pattern of the fiber type, so as to determine what kind of fiber the inspected fiber is. This requires a fiber atlas library covering all...

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): 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