Computer signal processing-based automatic detection method and system for surface defects of printed fabric

By combining ultrasonic transducer arrays and photoelectric position sensors, ultrasonic parameters are dynamically adjusted to perform multi-dimensional feature analysis and polygon area calculation, solving the problems of high false negative rate and low efficiency of traditional detection methods, and realizing high-precision automatic detection and sorting of defects in printed fabrics.

CN121275903BActive Publication Date: 2026-06-19CHENGDU IND VOCATIONAL TECHN COLLEGE
2 Cites 0 Cited by

Patent Information

Application Number
CN202511831449.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-12-08
Publication Date
2026-06-19
Estimated Expiration
2045-12-08

AI Technical Summary

Technical Problem

Traditional fabric defect detection methods suffer from high false negative rates and low efficiency, making it difficult to meet the high-precision detection requirements of high-speed production lines, especially in the detection of complex patterns and flexible fabrics.

Method used

By using an ultrasonic transducer array combined with a photoelectric position sensor, the edge position of the fabric is detected in real time, and the ultrasonic parameters are dynamically adjusted. Through multi-dimensional feature analysis and polygon area calculation algorithms, defect areas are located and classified.

Benefits of technology

It achieves high-precision and highly adaptable automatic detection of surface and near-surface defects in printed fabrics, meeting the quality control requirements of high-speed production lines, and enabling precise positioning, classification, and automatic sorting of defects.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

This invention provides an automatic detection method and system for surface defects of printed fabrics based on computer signal processing, belonging to the field of data processing technology. The method includes: setting an ultrasonic transducer array above the fabric's travel path, and fixing a photoelectric position sensor at the beginning and end of the path respectively; determining a virtual reference direction based on the fabric edge position information detected in real time by the two photoelectric position sensors; resolving the virtual reference direction into multiple continuous analysis intervals; evaluating the tension and smoothness properties of the fabric in each analysis interval to obtain dynamic adjustment values; and adjusting the emission parameters of the ultrasonic transducer array in real time based on the dynamic adjustment values, emitting controlled ultrasonic waves of a specific frequency onto the fabric surface, and receiving the reflected echoes to obtain the original acoustic signal data of the fabric. This invention achieves highly adaptable automatic detection of surface and near-surface defects in printed fabrics.
Need to check novelty before this filing date? Find Prior Art