一种基于车间制造的机械零部件角度无损精密测量方法
By using CCD or industrial cameras, telecentric lenses, and deep learning models in the mechanical parts measurement system, combined with shock-absorbing brackets and optical shielding devices, the problems of unstable image acquisition and low calibration accuracy of traditional angle measurement devices in workshop environments have been solved, achieving high-precision and stable angle measurement.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHENYANG TONGYI PETROCHEMICAL EQUIPMENT MANUFACTURING TECHNOLOGY CO LTD
- Filing Date
- 2026-04-01
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional angle measuring devices for mechanical parts suffer from insufficient image acquisition stability, low calibration accuracy, and drifting measurement results due to uneven light sources and vibration interference in workshop environments.
The system employs a combination of a CCD or industrial camera with a telecentric lens, a uniform light source, and a high-precision calibration plate, along with a shock-absorbing bracket and an optical shielding device. It utilizes a trained deep learning model to detect calibration reference points, performs multi-image calibration, and adaptively updates calibration parameters based on environmental information to achieve sub-pixel-level feature point localization and multi-point fitting.
In a workshop environment, high-precision, stable, and consistent measurement of part angles was achieved, improving image acquisition stability and calibration accuracy, and reducing measurement result drift.
Smart Images
Figure CN121953875B_ABST
Abstract
Citation Information
Patent Citations
CN101655361A
CN111612853A