A method and system for calculating a glass ribbon edge position and a draw edge wheel press edge parameter
By defining the mapping relationship between the image and camera coordinate systems and the world coordinate system, extracting key feature points and performing coordinate transformation, and combining Kalman filter calibration, the problem of insufficient accuracy in calculating the position of the edge puller and the edge of the glass strip and the edge pressing parameters in the existing technology is solved, and high-precision float glass production is realized.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BENGBU TRIUMPH ENG TECH CO LTD
- Filing Date
- 2026-01-07
- Publication Date
- 2026-06-05
AI Technical Summary
In existing technologies, image processing techniques suffer from poor image quality, low feature extraction accuracy, large coordinate transformation errors, severe model simplification, and poor dynamic adaptability. These issues result in insufficient accuracy in calculating the position of the edge puller and the edge of the glass strip, as well as the edge pressing parameters, thus affecting the production quality of float glass.
By defining the mapping relationship between the image coordinate system, camera coordinate system and world coordinate system, camera calibration is performed, key feature points are extracted and coordinate transformation is performed based on the camera projection model, and dynamic calibration is combined with Kalman filtering to optimize the calculation of edge compression parameters.
The calculation accuracy of the edge position of the edge-pulling wheel and the edge of the glass strip as well as the edge-pressing parameters has been improved, and the error caused by camera dynamic drift has been reduced, thus realizing high-quality float glass production.
Smart Images

Figure CN122156516A_ABST