The Three-dimensional Defect Detection And Classification System Design Of The Connector Array Pins

As an important part of intelligent manufacturing,3-D detection technology of workpiece assembly defects has always been a hot spot and frontier of domestic and foreign scholars.Its research contents mainly include 3-D point cloud reconstruction technology and 3-D workpiece assembly defect detection technology.The research contents of this dissertation are mainly from these two parts.Optical 3D measurement is widely used in the field of defect detection of electronic components.The detection and classification of three-dimensional defects of connectors is also a hot research topic.However,at present,there is still a big gap between the domestic three-dimensional defect detection system for electronic components and advanced foreign products.Based on this application background,the main content of this dissertation is the reconstruction technology of the optical threedimensional detection system and the detection and classification technology of connector pin defects.The work completed in this thesis mainly includes the following aspects.Firstly,the mainstream 3D reconstruction technology was investigated.According to the actual measurement requirements,a reconstruction model combining binocular stereo vision and structural grating was established.The hardware platform and software framework of the system are built according to the model.Secondly,the calibration model of the system is studied,and the main process of camera calibration is introduced.The key technologies involved in the 3D reconstruction process are described in detail,including image analysis of grating fringes and sinusoidal optical phase demodulation and phase unwrapping algorithms based on heterodyne multi-frequency.Next,the 3D point cloud processing algorithm applied in the connector pin defect detection and classification algorithm is introduced.Including point cloud filtering,point cloud streamlining,point cloud clustering and segmentation,and correction of point cloud parameter coordinate system.Finally,in order to verify the effectiveness of the 3D detection system built in this dissertation,this dissertation analyzes the reconstruction accuracy and reconstruction effect of the measurement system.The experimental results show that the reconstruction accuracy of the system is 0.021 mm,which meets the industrial measurement requirements.The validity of the 3D defect detection algorithm is tested by the pin defect detection of the connector and the coplanarity analysis of the pin.The experimental results show that the connector pin stereo defect detection and classification system built in this dissertation can complete the precise measurement of the connector and has certain robustness.