一种籽晶倾斜检测方法及装置
By collecting image sequences and torque information during the seed crystal rotation process, and combining visual and torque data, the problem of poor detection accuracy in existing technologies has been solved, and highly sensitive seed crystal tilt detection has been achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XIAN ESWIN MATERIAL TECHNOLOGY CO LTD
- Filing Date
- 2025-12-10
- Publication Date
- 2026-07-17
AI Technical Summary
Existing seed crystal tilt detection methods rely on the flatness of the liquid surface and the quality of reflection, which are easily affected by liquid surface fluctuations and uneven reflection, resulting in poor accuracy of detection results, especially for the identification of minute tilts.
By collecting image sequences and torque information during the seed crystal rotation process, and combining visual and torque dual-dimensional data, image recognition algorithms and frequency domain analysis are used to calculate the fitting center deviation and torque fluctuation characteristics, and to comprehensively judge the tilt state of the seed crystal.
It improves the accuracy of seed crystal tilt detection, reduces interference from single-dimensional detection, and enhances detection sensitivity and result reliability.
Smart Images
Figure CN121366283B_ABST