As intelligent manufacturing upgrades from single-point to system-wide, the role of industrial vision inspection in the electronics/PCBA industry has become increasingly important. In particular, the detection of hidden solder joints under BGA/QFN packages has become a key link in improving product quality. WeLinkirt's 3D AI AOI device provides an effective solution to this problem.
User Scenario: At the PCBA production line of a leading electronics manufacturer, after the BGA/QFN packaging process, it is necessary to detect the hidden solder joints on the circuit boards. BGA (Ball Grid Array) and QFN (Quad Flat No - leads) are common integrated circuit packaging forms, and the quality of their hidden solder joints directly affects the performance and reliability of electronic products.
Pain Points: In the trend of intelligent manufacturing upgrade, traditional 2D optical inspection methods have difficulty meeting the detection requirements of hidden solder joints under BGA/QFN packages. The traditional method has a relatively high miss-detection rate of about 3%, which means that a large number of defective products may enter the market. At the same time, the false-alarm rate is as high as 25%, resulting in a large amount of manpower being used for re-inspection, increasing production costs and production cycles. In addition, when changing product models, the programming time is long, about 30 minutes, seriously affecting production efficiency.
Technical Principle
WeLinkirt's 3D AI AOI device uses a self-developed 3D camera for imaging. The camera uses the structured light principle to project a specific light pattern onto the surface of the detection object and obtains the three-dimensional information of the object by analyzing the deformation of the reflected light. After obtaining the three-dimensional data, the device performs three-dimensional shape reconstruction and converts it into point-cloud data.
- For hidden solder joints, 2D optical inspection has blind spots, while 3D point-cloud data can clearly present the three-dimensional shape of the solder joints, including information such as height and shape. By analyzing this information, defects in hidden solder joints, such as cold solder joints and air holes, can be accurately detected.
- When detecting coplanarity, 3D point-cloud data can accurately measure the height difference of solder joints to determine whether they meet the coplanarity requirements. For the detection of micron-level morphology, the high precision of 3D imaging can capture tiny surface changes, ensuring the accuracy of detection.
- The 2D-3D fusion technology combines the texture information of 2D images and the geometric information of 3D point-clouds, further improving the comprehensiveness and accuracy of detection.
WeLinkirt's Solution and Product
Centered around the 3D AI AOI device, WeLinkirt provides a complete inspection solution. The self-developed 3D camera and three-dimensional shape reconstruction technology of this device can effectively detect hidden solder joints, coplanarity, micron-level morphology, and air holes in 2D optical blind spots under BGA/QFN packages. The supporting DaoAI AI AOI software system has the feature recognition ability of a visual basic model. It can achieve zero-code automatic programming for a good product in 5 minutes. It uses APDT positive-sample/few-sample learning (1-20 good samples) and reduces false alarms through the semantic false-alarm filtering function.
The 3D AI AOI device brings new breakthroughs to the BGA/QFN packaging inspection in the electronics/PCBA industry with its advanced technology.
Quantitative Results: After using WeLinkirt's 3D AI AOI device, the detection rate reaches 99.2%, and the miss-detection rate is reduced to <0.8%, greatly reducing the risk of defective products entering the market. The false-alarm rate is reduced by -68%, effectively reducing the manpower and time cost of re-inspection. The product model change time is shortened from 30 minutes to 5 minutes, significantly improving production efficiency.