Yarn Spindle Defect Detection With Neural Network Grading
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The chemical fiber industry faces inefficiencies in defect detection and level evaluation of yarn spindles, which are heavily dependent on manual experience, affecting production and management efficiency.
Innovation Solution
A method and apparatus for automated defect detection and level evaluation of yarn spindles using a neural network model, such as DWWA-Net, to identify defects and adjust levels based on detection results, eliminating the need for manual intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual defect detection and level evaluation methods are used, then workers can perform defect detection on individual yarn spindles, but the detection method is highly dependent on manual experience and is inefficient
Solution Approach 1:
The patent replaces the manual mechanical inspection system with an automated optical detection system. Image acquisition devices capture images of yarn spindles, and a neural network model automatically analyzes these images to detect defects and evaluate quality levels, substituting human visual inspection with machine-based automated detection.
Solution Approach 2:
The system enables self-service through automated defect detection and level evaluation. The neural network model independently analyzes yarn spindle images, automatically determines defect presence and quality levels without requiring manual intervention, allowing the system to serve itself in the detection and evaluation process.
2Productivity
If automated defect detection is implemented, then detection efficiency is improved, but the system complexity increases
Solution Approach 1:
The patent introduces an intermediary neural network model that bridges image acquisition and defect detection. The model serves as a mediator that processes raw images and translates them into defect detection results and quality level evaluations, simplifying the overall system architecture while maintaining high detection efficiency.
Data Source
AI summary
A method for processing yarn spindle data, an electronic device and a storage medium, relating to the field of data processing technology, are provided. The method includes: after determining that a yarn spindle is transported into a detection area, performing a defect detection on the yarn spindle located in the detection area to obtain a target detection result of the yarn spindle. The target detection result is used to characterize a defect degree of the yarn spindle. The method further includes: after determining that the target detection result meets a preset defect value, obtaining a target level of the yarn spindle based on the target detection result of the yarn spindle and a preset level of the yarn spindle.