Machine Vision-Based Online Detection System and Method for Yarn Hairiness in Texturing Machines

By using pneumatic yarn guiding cleaning and dual-band color difference imaging technology, the imaging problem of yarn hairiness detection in high-speed production of texturing machines has been solved. High signal-to-noise ratio imaging has been achieved in environments with high concentration of oil mist and yarn vibration, ensuring the accuracy and stability of yarn hairiness detection.

CN121721044BActive Publication Date: 2026-05-26XIAN HUODE IMAGE TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202610206029.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-02-12
Publication Date
2026-05-26
Estimated Expiration
2046-02-12

AI Technical Summary

Technical Problem

In the high-speed production environment of texturing machines, existing technologies struggle to achieve high signal-to-noise ratio microscopic imaging under conditions of high-concentration oil mist interference and random micro-movement of yarn, especially in distinguishing between yarn fuzz and environmental noise.

Method used

The system employs a pneumatic yarn guiding cleaning unit and a dual-band chromatic aberration imaging unit. It cleans the optical window through high-speed laminar flow and forms an air cushion layer. Combined with a multi-band light source and a fixed-focus chromatic aberration lens, it achieves stable imaging of the yarn. The image processing unit performs pixel-level suppression and correction to remove stains and noise.

Benefits of technology

It achieves clear imaging of yarn in harsh industrial environments, ensuring that the detection system can acquire interference-free intrinsic yarn images without contacting damaged yarn, thus improving the accuracy and stability of yarn hair detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121721044B_ABST
    Figure CN121721044B_ABST
Patent Text Reader

Abstract

This invention discloses an online detection system and method for yarn hairiness in texturing machines based on machine vision, belonging to the field of textile automation detection technology. The system includes a pneumatic yarn guiding and cleaning unit, a dual-band color difference imaging unit, and an image processing unit. The pneumatic yarn guiding and cleaning unit utilizes an airflow guiding structure to generate a high-speed laminar flow parallel to the optical window. This high-speed laminar flow simultaneously performs the functions of cleaning the window and constraining the yarn within an air cushion layer using hydrodynamic pressure. The dual-band color difference imaging unit utilizes axial color difference characteristics to focus the first band on the window surface and the second band on the air cushion layer. The image processing unit uses the first band data to quantify the features of deposits on the window surface and performs pixel-level suppression on the second band data accordingly. This invention solves the imaging detection problem caused by the coupling of yarn vibration and stain interference in the high-speed oil mist environment of a texturing machine through the physical coupling of pneumatic constraint and spectral layering.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Method for automatically segmenting multi-band image by adaptive filter

    CN101882303A

  • PE fiber yarn quality online detection equipment and method based on machine vision

    CN112485263A