Supercharge Your Innovation With Domain-Expert AI Agents!

Heddle separation detection system and method based on self-learning mode

A detection method and detection system technology, which can be used in optical testing of flaws/defects, material analysis by optical means, measurement devices, etc. Improve the accuracy of classification and detection, improve the efficiency of classification and detection, and reduce the effect of machine errors

Pending Publication Date: 2020-03-06
李守斌
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the existing technology, because the sensitivity of the machine cannot meet the standard or is not ideal, or the machine is aging and other reasons, there are often problems that the machine hooks by mistake or does not hook the yarn during the hooking process, resulting in the product not reaching the ideal level.
At present, image detection technology has become more and more mature, and it has been gradually applied in quality inspection. However, due to the complexity and variety of yarn types, traditional image detection cannot be a good solution in the case of multiple samples and multiple scenarios. Program

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
  • Heddle separation detection system and method based on self-learning mode
  • Heddle separation detection system and method based on self-learning mode
  • Heddle separation detection system and method based on self-learning mode

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] This embodiment provides a heald separation detection system based on the self-learning mode, such as Figure 1 to Figure 2 Shown:

[0043] It includes an image acquisition unit for sample image acquisition of the yarn to be tested, a sample preprocessing module for preprocessing the sample image, a defect detection module for detecting defect areas on the preprocessed image, and a defect detection module for the preprocessed image The feature extraction module for feature vector extraction of the detected defect area image is used to store the yarn information database of each standard yarn information, and is used to classify and single / multiple yarns to be tested according to the feature vector and each standard yarn information The yarn classification detection module for yarn judgment, and the PC control terminal for corresponding heald separation control according to the yarn classification results to be tested and the single / multi-yarn judgment results. The yarn...

Embodiment 2

[0045] The heald separation detection method based on the self-learning mode comprises the following steps:

[0046] S1. Hook the yarn to be tested, and collect the sample image of the yarn to be tested;

[0047] S2. Preprocessing the collected sample image;

[0048] S3. Perform defect area detection on the preprocessed image, and extract the image of the defect area;

[0049] S4. Extract feature vector information from the defect area image, and at the same time perform classification information extraction on the preprocessed image corresponding to the defect area image;

[0050] S5. According to the characteristic vector information and classification information, classify the yarn to be tested and judge single / multi-yarn, and perform corresponding heddle separation control according to the judgment result.

Embodiment 3

[0052] As an optimization of the above-mentioned embodiment, the process of preprocessing the sample image includes: firstly performing the following steps on the sample image image 3 The image data shown is processed, then image noise reduction processing is performed, and finally image enhancement processing is performed. Such as Figure 4 As shown, mean downsampling is performed on the enhanced image, bilinear interpolation is performed after mean downsampling, and then variance downsampling is performed, and bilinear interpolation is performed after variance downsampling.

[0053] After we obtain the sampled image, the next step is to process it into data, that is, to convert all the information in the image into a form that can be processed by a computer. Specifically, the image is divided into small areas called pixels as shown in the figure below, and the gray value or brightness of each pixel is represented by an integer. In this way, a digital image can be formed, ...

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 the technical field of textile, in particular to a heddle separation detection system and method based on a self-learning mode. The system comprises an image acquisition unitwhich is used for performing sample image acquisition on a to-be-detected yarn; a sample preprocessing module which is used for preprocessing the sample image; a defect detection module which is usedfor carrying out defect area detection on the preprocessed image; a feature extraction module which is used for carrying out feature vector information extraction on the detected defect area image; ayarn information database which is used for storing standard yarn information; a yarn classification detection module which is used for carrying out to-be-detected yarn classification and single / multi-yarn judgment according to the feature vector information and the standard yarn information; and a PC control terminal which is used for carrying out corresponding harness wire separation control according to a to-be-detected yarn classification result and a single / multi-yarn judgment result. According to the invention, the intelligent yarn classification and single / multiple yarn detection can becarried out on yarns in the heddle separation process, the yarn classification and detection efficiency is effectively improved, and the machine error is reduced.

Description

technical field [0001] The invention relates to the technical field of textiles, in particular to a heald separation detection system and method based on a self-learning mode. Background technique [0002] The traditional handicraft textile technology has gradually begun to be replaced by automated assembly line industrial production. In the production field of the yarn industry, through the complete industrial assembly line process, we can realize the release of hundreds of millions of output per day. Faced with such a large Quantity and quality issues become more important. In the weaving process, it is necessary to accurately separate the heald components from the stacking queue and send them to the lead wire system at high speed, store the healds in the heald storage place at one time, and then transport them to the corresponding process position on the automatic threading for single piece The heddle is separated, and the subsequent process is carried out after separati...

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): G01N21/88
CPCG01N21/8851G01N2021/8887G01N2021/8883G01N2021/8874
Inventor 李守斌唐冲刘洋洋
Owner 李守斌
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com