In the electronics/PCBA industry, accurate detection of PCB silk - screen/OCR characters is crucial. WeLinkirt provides an efficient detection solution for this industry with advanced AI vision technology.
User scenario: In the production line of a leading electronics/PCBA manufacturer, after the board - level assembly process, it is necessary to detect the silk - screen and OCR characters on the printed circuit board (PCB). These silk - screen and characters contain important information such as product models, batch numbers, and dates, which are crucial for product traceability and quality control.
Pain points: Traditional detection methods have many problems. On the one hand, due to the reflective properties of the PCB surface, especially in some mirror - like metal areas, the 3D point cloud is sparse, noisy, and missing, resulting in pose and detection failures. The miss - detection rate reaches 3%. On the other hand, manual detection is inefficient, with a false - alarm rate as high as 15%, and the labor cost is high. At the same time, when changing the production line model, reprogramming takes a lot of time. The average model - changing time reaches 30 minutes, seriously affecting production efficiency.
Technical Principle
WeLinkirt uses multi - view active vision technology to solve the above problems. This technology uses multiple cameras from different angles to image the PCB simultaneously and uses an active light source to reduce the impact of reflection. At the algorithm level, deep learning algorithms are used to extract and analyze the features of the collected images. The deep learning model has a powerful feature - learning ability and can accurately identify silk - screen and OCR characters from complex images. In addition, through the fusion processing of images from different perspectives, the missing 3D point cloud can be compensated, and the accuracy of pose detection can be improved. Because images from different perspectives contain more information, and after fusion, they can more comprehensively reflect the real situation of the PCB, thus effectively solving the detection problems caused by reflection.
- Multi - view imaging: Obtain PCB images from multiple angles to reduce reflective occlusion.
- Active light source: Provide stable lighting conditions to reduce reflective interference.
- Deep learning algorithm: Accurately extract silk - screen and character features to improve recognition accuracy.
- Image fusion: Integrate images from different perspectives to improve 3D point cloud information.
WeLinkirt Solution and Products
WeLinkirt provides the DaoAI AI AOI software system and the DaoAI 2D / 3D AI AOI equipment. The DaoAI AI AOI software system is based on the feature recognition of the visual basic model and can achieve 0 - code automatic programming in 5 minutes for a single good product. Through APDT positive - sample/few - sample learning (only 10 good products are needed), an accurate detection model can be quickly established. At the same time, the semantic false - alarm filtering function can effectively reduce the false - alarm rate. The DaoAI 2D / 3D AI AOI equipment is equipped with a self - developed 3D camera, which can perform three - dimensional shape reconstruction, detect hidden solder joints, coplanarity, and micron - level morphology, providing more accurate basic data for silk - screen and character detection. During the implementation process, the equipment is installed on the production line, and the software is integrated with the equipment to achieve automated detection.
WeLinkirt's AI vision technology brings an efficient and accurate solution for PCB silk - screen/OCR character detection in the electronics/PCBA industry.
Quantitative results: After using WeLinkirt's solution, the detection rate has increased to 98%, and the miss - detection rate has decreased to <2%. The false - alarm rate has decreased by - 60%, from the original 15% to 6%. The production line model - changing time has been significantly shortened, from 30 minutes to 5 minutes, greatly improving production efficiency.