Research Of Connector Inspection And Location Technology Based On Machine Vision

Recently, the assembly of most of standardized electronic components can be performed fast and stably by Surface mount devices. For other special-shaped and non-standardized electronic components, most are hand-assembled due to its complex structure and special shape. With the rapid development of China’s electronic industry, and to improve existing production processes, eliminate unstable factors in the production process. Under this background, the demand for non-standardized electronic components automatic plug-in is more and more urgent, quality detection and precise positioning of non-standardized electronic components is essential production processes during automatic insertion process.In allusion to the problems mentioned above, this paper applies the machine vision detection and location technology to the assembling process of non-standardized electronic components and realizes the non-contact real-time detection and automatic instrumentation for the non-standardized electronic components. It overcomes the problem of poor reliability and low efficiency in the artificial detection method, and improves the production efficiency and the quality of electronics products. The main contributions of this paper are as follows:1. In order to get high quality images, the lighting and image acquisition solutions of the machine vision detection system are studied and analyzed in details. And a visual inspection system is constructed based on lighting experiment, and it establishes a basis for the future work of image processing.2. Aiming at defects detection of pins, traditional method Blob analysis of Electronic component pins detection has been studied, it is a method of extracting similar regions from connected region of binary image based on its geometric features, but Blob analysis is not a stable algorithm because it is sensitive to the illumination disturbance and noise interference, so it exists fault inspection. Therefore, a template matching method based on edge points and its gradient directions is used to detect all pins at the same time.Experimental results demonstrate that the algorithm can obtain good matching results in the case of target rotation, noise interference and illumination disturbance, so it can decide fast and accurately whether electronic connectors is good or not.3. Aiming at precise assembly of connectors, the proposed visual inspection and location system employs a local coordinate system to locate the jack position on the printed circuit board, which was created by the relative position of two mark points; employs the coordination of alignment posts to locate the pose of connector, and the center of alignment post has become the rotation center of the robot through coordinate translation. Moreover,the assembly precision is not affected by the rotation and offset of printed circuit board and connector itself.4. The experimental results demonstrate that inspection and location algorithms have high precision, and it can meet the real-time and accuracy requirements of connectors assembled automatically.