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

Method based on textile fiber identification and component detection system

A technology for the detection of textile fibers and components, which is used in measuring devices, analysis materials, and material analysis by optical means. Effect

Pending Publication Date: 2020-09-15
温力力 +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] 1) The chemical method will produce a large amount of sulfuric acid waste liquid, etc., which will seriously pollute the testing site and endanger the health of testing personnel. According to the national environmental protection requirements, it cannot be discharged and is difficult to recycle;
[0004] 2) The entire process is implemented manually, which is inefficient, consumes a lot of human resources, and has high labor costs;
[0005] 3) The staff of the Textile Inspection Institute use the microscope to observe for up to 8-10 hours a day. The time is long, the intensity is high, and the repeatability is strong. Working for a long time will cause fatigue, resulting in a decrease in accuracy

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
  • Method based on textile fiber identification and component detection system
  • Method based on textile fiber identification and component detection system
  • Method based on textile fiber identification and component detection system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] see Figure 1 to Figure 3 , a method based on textile fiber identification and component detection system, mainly includes the following steps:

[0053] 1) Establish a fiber intersection location model, an abnormal fiber filtering model, and a fiber identification and quality analysis model, and store them in the host computer.

[0054] The main steps of establishing the fiber intersection location model are as follows:

[0055] 1) Using an optical imaging system to acquire several crossing fiber images of the same size, marking and labeling the fiber crossing points in the crossing fiber images.

[0056] II) Based on the marked cross-fiber images, respectively establish a cross-fiber training set and a cross-fiber validation set.

[0057] III) Input the cross-fiber training set into the neural network to train the neural network.

[0058] IV) Input the cross-fiber verification set into the neural network, verify the neural network, and adjust the parameters of the n...

Embodiment 2

[0132] A method based on textile fiber identification and component detection system, the main steps are as follows:

[0133] 1) The optical imaging system performs optical imaging on the sample to be tested.

[0134] The camera shoots the optical images of the samples to be tested, obtains images of several samples to be tested, and sends them to the host computer.

[0135] 2) The host computer sequentially imports the images of several samples to be detected into the fiber intersection location model, so as to automatically locate and delete the fiber intersections in the images.

[0136] The main steps of fiber intersection localization model to delete fiber intersection are as follows:

[0137] 1) find the intersection center position according to the fiber intersection location model.

[0138] II) In the image, determine a circular area C with the center of the intersection point as the center and the fiber width in the image as the radius. The radius error is [xx,xx]....

Embodiment 3

[0146] A method based on textile fiber identification and component detection system, the main steps are as follows:

[0147] 1) The optical imaging system performs optical imaging on the sample to be tested.

[0148] The camera shoots the optical images of the samples to be tested, obtains images of several samples to be tested, and sends them to the host computer.

[0149] 2) The host computer sequentially imports the images of several samples to be detected into the fiber intersection location model, so as to automatically locate and delete the fiber intersections in the images.

[0150] The main steps of fiber intersection localization model to delete fiber intersection are as follows:

[0151] 1) find the intersection center position according to the fiber intersection location model.

[0152] II) In the image, determine a circular area C with the center of the intersection point as the center and the fiber width in the image as the radius. The radius error is [xx,xx]....

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

PropertyMeasurementUnit
Lengthaaaaaaaaaa
Fiber widthaaaaaaaaaa
Lengthaaaaaaaaaa
Login to View More

Abstract

The invention discloses a method based on a textile fiber identification and component detection system. The method comprises the following main steps: 1) establishing a fiber intersection point positioning model, an abnormal fiber filtering model and a fiber identification and quality analysis model; 2) determining a to-be-detected sample; 3) acquiring an image of the to-be-detected sample by using an optical imaging system; 4) obtaining a plurality of images only containing a single fiber; 5) obtaining a plurality of normal fiber images; 6) importing the plurality of normal fiber images intothe fiber identification and quality analysis model, identifying the types of fibers in each normal fiber image, and calculating the fiber quality; and 7) an upper computer obtaining the component ratio of each type of fibers based on the types and the mass of the fibers. Automatic identification of the components of the to-be-detected textile and automatic analysis of the component mass ratio are realized.

Description

technical field [0001] The invention relates to the field of textile fiber component detection, in particular to a method based on a textile fiber identification and component detection system. Background technique [0002] At present, the detection of textile components is mainly carried out manually, and the traditional methods include chemical methods and microscope observation methods. The chemical method mainly uses the dissolution characteristics of different chemical reagents to different fibers at different temperatures to quantitatively analyze the components of some fibers. The process of microscope observation method is that the inspector makes the textile sample to be tested as a glass slide, manually adjusts the movement of the microscope, uses the naked eye to distinguish the microscopic shape of the textile fiber, judges the type of the sample fabric, and measures the size. The traditional textile composition detection methods mainly have the following defect...

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): G01N21/84G01N21/01
CPCG01N21/84G01N21/01G01N2021/8444G01N2021/0112Y02P90/30
Inventor 龚晟麦晓霞张晓利王子石高茂胜樊哲新王文余娟杨知方温力力
Owner 温力力