Circular knitting machine cloth cover defect online detection device and detection method based on main / auxiliary double camera shooting mode
By installing a camera and an edge computing platform on the linkage rod of the round-weather rolling frame, combining industrial cameras and backlights, and using the YOLOv5 model for real-time detection and classification, the missing detection and hysteresis problems in the online detection of defects on the round-weather surface is solved, and efficient and accurate defect detection is achieved.
Patent Information
- Application Number
- CN202411967124.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-30
- Publication Date
- 2025-03-18
AI Technical Summary
In the prior art, there are problems of missing detection and hysteresis in online detection of defects on the surface of round weft machines, especially the problems of missing detection caused by the shackle linkage rod blocking are difficult to solve.
Using a detection device based on the main/submarine dual camera method, a camera and an edge computing platform are installed on the rolling frame linkage linkage, combined with an industrial camera and a backlight, the cloth image of the obstructed part is collected and detected, and the YOLOv5 model is used for real-time detection and classification, to determine the type of defects and decide whether to shut down.
It realizes comprehensive, accurate and fast online detection of defects on the surface of the round weft machine, avoids missed inspection problems, and improves the timeliness and accuracy of the inspection through real-time detection and classification functions.