Spinning Box Defect Detection with Image-Based Deep Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual detection methods for defects in spinning boxes are inefficient, reliant on experience, and prone to errors, affecting yarn production quality and efficiency due to issues like yarn floating, breakage, and misalignment.
Innovation Solution
An automated spinning box detection method using a target detection model, such as a dynamic weights-based wavelet attention neural network, to identify defects like yarn floating and misalignment by analyzing images of the spinning box.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual detection method is used, then detection can be performed, but detection efficiency is low and detection accuracy is poor
Solution Approach 1:
The patent replaces the manual mechanical detection system with an automated image-based detection system using deep learning models. The target detection model processes images of the spinning box to automatically identify defects, eliminating the need for manual inspection and significantly improving both detection efficiency and accuracy.
Solution Approach 2:
The patent creates a digital copy (image) of the spinning box interior and processes this copy through the target detection model. This allows defect detection to be performed on the image representation rather than requiring direct manual inspection of the physical spinning box, enabling automated high-accuracy detection.
2Reliability
If manual detection is performed, then defect identification is possible, but it relies heavily on operator experience
Solution Approach 1:
The detection system performs self-service by automatically analyzing images and identifying defects without requiring human operators. The target detection model independently processes images, detects defects, and provides results, eliminating reliance on operator experience and ensuring consistent detection quality.
Solution Approach 2:
The patent transforms the detection process from subjective human judgment to objective parameter-based analysis. The target detection model analyzes specific image parameters (pixel values, patterns, features) to objectively identify defects, replacing experience-based subjective assessment with quantifiable parameter analysis.
3Loss of time
If manual detection is used, then inspection can occur, but time consumption is high
Solution Approach 1:
The detection system enables continuous operation by processing images automatically without interruption. Multiple images can be processed in sequence without stopping production, and the target detection model continuously analyzes incoming images to identify defects, eliminating the time loss associated with manual detection intervals.
Solution Approach 2:
The system performs preliminary detection by analyzing images taken during normal production operations. Defects are identified in advance before they affect product quality, allowing timely corrective actions without interrupting the production flow, thus reducing overall detection time and improving production efficiency.
Data Source
AI summary
Provided is a spinning box detection method, an electronic device and a storage medium. The method includes: obtaining an image to be detected of a spinning box when determining that the spinning box meets a preset defect detection condition; and inputting the image to be detected into a target detection model to obtain a target detection result of the spinning box; wherein the target detection model is used to detect whether there is a defect in the spinning box to obtain the target detection result; and the target detection result comprises at least one of: a total quantity of defects, a defect position or a defect type.