Against the background of the 'computational moment' of industrial mother machines, industrial vision quality inspection is being upgraded to large-model applications. WeLinkirt's 3D AI AOI equipment brings innovation to the detection of automotive/parts gluing and sealing.
User Scenario: A leading automotive parts supplier has a gluing/sealing process in its automotive parts production line. The products are various automotive parts, and the detection objects are the sealing conditions after parts gluing, including the thickness, width, continuity of the glue layer, and the accuracy of the sealing path.
Pain Points: In the 'computational moment' of industrial mother machines, traditional industrial vision quality inspection methods struggle to adapt to the upgrade of automation equipment to large-model applications. The supplier faces numerous quantitative difficulties in the gluing and sealing detection process. The miss-detection rate reaches 3%, causing some products with sealing defects to enter subsequent processes, increasing rework costs. The false-alarm rate is as high as 20%, and frequent false alarms lead to frequent production line shutdowns, reducing production efficiency. Manual inspection is not only inefficient but also incurs high labor costs. Moreover, the model-change time is as long as 30 minutes, failing to meet the requirements of rapid model changes. In addition, industry compliance requirements for the precision and comprehensiveness of sealing detection are constantly increasing, and traditional detection methods fall short.
Technical Principle
WeLinkirt's 3D AI AOI equipment uses a self-developed 3D camera for image acquisition. The 3D camera utilizes the structured-light principle, projecting a specific structured-light pattern onto the surface of the object to be measured. The camera captures the deformed light pattern reflected from the object's surface. Since the height changes on the object's surface cause the deformation of the light pattern, the three-dimensional coordinates of each point on the object's surface can be calculated based on the degree of deformation, thereby achieving three-dimensional shape reconstruction.
- For defects in 2D optical blind spots such as hidden solder joints, coplanarity, and micron-scale morphology, the 3D point-cloud data after reconstruction can provide more abundant information. By analyzing the three-dimensional point-cloud data, these defects can be accurately identified. For example, for hidden solder joints, the presence and welding quality of the solder joints can be judged by analyzing the three-dimensional morphological features around the joints.
- In terms of 2D-3D fusion, the texture information of the 2D image is combined with the geometric information of the 3D point cloud. The 2D image can provide information such as the color and texture of the object's surface, while the 3D point cloud provides the three-dimensional shape information of the object. After fusion, the detection object can be analyzed and judged more comprehensively and accurately.
- In the gluing/sealing detection, by reconstructing and analyzing the three-dimensional morphology of the gluing area, the parameters such as the thickness, width, and continuity of the glue layer can be accurately measured. Meanwhile, by comparing the actual gluing path with the preset sealing path model, path correction can be achieved.
WeLinkirt's Solution and Product
Centered around the 3D AI AOI equipment, this device has high-precision 3D imaging and analysis capabilities, enabling 100% online 3D detection of the gluing and sealing conditions of automotive parts. During the detection process, the device can collect real-time three-dimensional data of the gluing area and compare it with the preset standard model.
WeLinkirt's 3D AI AOI equipment provides a more comprehensive and accurate solution for automotive gluing and sealing detection through 2D-3D fusion technology.
The supporting DaoAI AI AOI software system enables rapid programming. Automatic programming without code can be completed in 5 minutes for a good-quality product. Combined with the APDT positive-sample/few-sample learning (only 1-20 good-quality samples are required) and semantic false-alarm filtering functions, the detection efficiency and accuracy are further improved. At the same time, the system can generate real-time correction instructions based on the detection results to guide the gluing equipment for path correction.
Quantitative Results: After introducing WeLinkirt's 3D AI AOI equipment, the detection rate of the supplier's gluing and sealing detection has increased to 99%, and the miss-detection rate has been reduced to <1%, effectively preventing defective products from entering subsequent processes. The false-alarm rate has been reduced by -60%, reducing the number of production line shutdowns caused by false alarms and improving production efficiency. The model-change time has been shortened from 30 minutes to 5 minutes, meeting the requirements of rapid model changes.
FAQ
What gluing and sealing defects can the 3D AI AOI equipment detect?
The equipment can detect problems such as uneven glue-layer thickness, inconsistent width, and poor continuity. It can also detect defects in 2D optical blind spots like hidden solder joints, providing comprehensive detection through 3D reconstruction and 2D-3D fusion technology.
Is the programming of the supporting software system complicated?
No, it's not. The DaoAI AI AOI software system supports automatic programming without code, which can be completed in 5 minutes for a good-quality product. Combined with APDT positive-sample/few-sample learning, only 1-20 good-quality samples are required.
How much can the model-change time be shortened after using this equipment?
The model-change time can be shortened from 30 minutes to 5 minutes, meeting the requirements of rapid model changes in the automotive parts production line.