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

Polyester filament yarn broken filament detection method

A polyester filament yarn and detection method technology, which is applied in the directions of measuring devices, optical testing for flaws/defects, image enhancement, etc., can solve problems such as inability to realize silk cake detection, inability to detect on-line at high speed, and limited detection speed, etc., to achieve Improve detection accuracy and stability, improve stability and accuracy, and overcome the effect of false detection

Active Publication Date: 2020-08-07
JIANGSU HENGLI CHEM FIBER
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In actual production, the polyester wool is very small and almost invisible to the naked eye. It can only be detected by visual inspection of the number of wool on the surface and end face of the entire yarn cake, and the detection of wool inside the yarn cake cannot be realized.
The existing patent application 201611036029.0 for the hair detection method based on image processing uses an industrial area array camera to collect images of viscose filaments, and performs a series of image processing operations on them to achieve the separation and detection of hairs, although it can be accurately realized The number and length of wool filaments are detected, but the amount of calculation is large and the detection speed is limited, so it cannot be used for high-speed online detection

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
  • Polyester filament yarn broken filament detection method
  • Polyester filament yarn broken filament detection method
  • Polyester filament yarn broken filament detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] A method for detecting polyester filament wool, the steps are as follows:

[0045] (1) Training stage:

[0046] (1.1) Collect 1-line image of a hairless silk sample (polyester filament, specification 189dtex / 96f) through a line-scan camera, denoted as x 1 , x 1 ∈ R 1024 ;

[0047] (1.2) Use filter F to x 1 Perform filtering operation to get y 1 ; filter F = [1 1 1 1 1]; y 1 ∈ R 1024 ;

[0048] (1.3) Calculate y 1 the average value of

[0049] (1.4) Binarization: use to y 1 Perform binarization, greater than The pixel of is assigned a value of 1, which is less than or equal to The pixel is assigned a value of 0, and the binarized image A is obtained 1 ;

[0050] (1.5) Get the diameter: Statistics A 1 A connected region in , and A 1 The number of pixels contained in the largest connected area in is taken as the diameter of the polyester filament, which is denoted as d 1 = 41;

[0051] (1.6) Collect 5,000 lines of images of hairless silk samples thr...

Embodiment 2

[0065] A method for detecting polyester filament wool, the steps are as follows:

[0066] (1) Training stage:

[0067] (1.1) Collect 1-line image of the hairless silk sample (polyester filament, 167dtex / 128f) through a line-scan camera, denoted as x 1 , x 1 ∈ R 1024 ;

[0068] (1.2) Use filter F to x 1 Perform filtering operation to get y 1 ; filter F = [1 1 1 1 1]; y 1 ∈ R 1024 ;

[0069] (1.3) Calculate y 1 the average value of

[0070] (1.4) Binarization: use to y 1 Perform binarization, greater than The pixel of is assigned a value of 1, which is less than or equal to The pixel is assigned a value of 0, and the binarized image A is obtained 1 ;

[0071] (1.5) Get the diameter: Statistics A 1 A connected region in , and A 1 The number of pixels contained in the largest connected area in is taken as the diameter of the polyester filament, which is denoted as d 1 = 32;

[0072] (1.6) Collect 20,000 lines of images of hairless silk samples through a lin...

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 relates to a polyester filament yarn broken filament detection method. The method comprises the following steps: (1) a training stage: collecting a row of images x1 of a broken filament-free sample through a linear array camera; filtering x1 by using a filter to obtain y1; carrying out binarization on y1 to obtain A1; counting the number of pixels contained in the maximum communication area in A1 to serve as the diameter d1; repeating the previous steps on the N rows of images of the non-broken filament sample to obtain the diameter {dn} of the non-broken filament sample; adopting gaussian distribution to model {dn} to obtain mu and sigma < 2 >; (2) adopting mu and sigma 2 to perform detection, collecting K rows of images {xk} of a sample to be detected through a linear arraycamera; performing filtering by using a filter to obtain yk; carrying out binarization on the yk to obtain Bk; counting the diameter {dk} in Bk and the number {pk} of the pixel points equal to a ', in {dk}, when dk is greater than mu + c sigma or c is greater than or equal to 3 and less than or equal to 5, determining that broken filaments exist in the to-be-detected sample, otherwise, determining that broken filaments do not exist in the to-be-detected sample.

Description

technical field [0001] The invention belongs to the field of quality detection methods of chemical fiber filaments, and relates to a detection method of polyester filament wool. Background technique [0002] Fuzz is the main appearance defect of polyester filament yarn, and the number of fuzz will directly affect the efficiency of downstream weaving and dyeing processes and the quality of finished products. Polyester filaments are usually processed by a network of multi-strand monofilaments with extremely small diameters. The wool is formed by stretching or breaking some monofilaments due to various external forces and protruding from the surface of the yarn body. In actual production, the polyester wool is very small and almost invisible to the naked eye. It can only be detected by visual inspection of the number of wool on the surface and end face of the entire yarn cake, and it is impossible to detect the wool inside the yarn cake. The existing patent application 2016110...

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): G06T7/00G06T7/62G06T5/00G06T5/20G01N21/88G01N21/952G01B11/00G01B11/08
CPCG06T7/0004G06T7/62G06T5/20G01N21/8851G01N21/952G01B11/00G01B11/08G06T2207/10004G06T2207/30124G01N2021/8887G01N2021/8874G01N2021/8883G06T5/70
Inventor 周建尹立新汤方明王丽丽魏存宏
Owner JIANGSU HENGLI CHEM FIBER
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