In the wave of intelligent manufacturing, the combination of industrial vision quality inspection and world model technology has become the key to improving the accuracy of defect detection. WeLinkirt's 3D AI AOI equipment plays an important role in the inspection of aluminum die-castings in the automotive/parts industry.
User scenario: A leading automotive parts supplier, on the aluminum die-casting production line, mainly produces aluminum die-castings for key parts such as automobile engines. The detection objects are X-ray porosity and inclusion defects inside the aluminum die-castings. These defects may affect the strength and reliability of automotive parts, and further affect the performance and safety of the whole vehicle.
Pain points: In traditional detection methods, there are many quantitative dilemmas. The miss-detection rate is relatively high, reaching about 4%, which means that some defective aluminum die-castings may flow into subsequent processes, increasing the quality risk of products. The false-alarm rate is as high as 35%. Frequent false alarms not only waste a lot of manpower for re-inspection but also reduce production efficiency. In addition, the model-changing time of traditional detection equipment is long, about 30 minutes, which cannot meet the production demand for rapid model-changing. Combining with today's hot-spot direction, traditional detection methods fail to make full use of world model technology, making it difficult to accurately identify and detect complex defects, resulting in limited detection accuracy.
Technical principle
WeLinkirt's 3D AI AOI equipment uses self-developed 3D cameras and advanced three-dimensional topography reconstruction/point cloud technology. The self-developed 3D camera can capture the three-dimensional information of aluminum die-castings, providing rich data for subsequent analysis. The three-dimensional topography reconstruction algorithm accurately reconstructs the real topography of aluminum die-castings based on these data. Point cloud technology represents the three-dimensional coordinate information of the object surface in the form of points. By analyzing the point cloud data, hidden solder joints, coplanarity, micron-level topography, and defects such as porosity in the 2D optical blind area can be clearly identified. This is because 2D detection can only obtain the planar information of the object, and it is difficult to detect internal porosity and inclusion defects. However, 3D technology can observe the object from multiple dimensions, thus effectively detecting these hidden defects. At the same time, the equipment uses 2D-3D fusion technology, combining the texture information of 2D images and the depth information of 3D models to further improve the accuracy of defect detection.
- The self-developed 3D camera provides high-precision three-dimensional data.
- The three-dimensional topography reconstruction algorithm accurately restores the real topography of the object.
- Point cloud technology can effectively identify defects in the 2D optical blind area.
- 2D-3D fusion technology combines two kinds of data to improve detection accuracy.
WeLinkirt solution and product
Centered on the 3D AI AOI equipment, this equipment has high-precision detection ability and can detect micron-level porosity and inclusion defects inside aluminum die-castings. In terms of implementation, first, according to the specific needs and product characteristics of customers, the DaoAI AI AOI software system is used for programming. This software system has the feature-recognition ability of the visual basic model. It only takes 5 minutes to complete zero-code automatic programming with one good product, and uses APDT positive-sample/few-sample learning (1-20 good products), greatly shortening the programming time and cost. At the same time, combined with the DaoAI World model, semantic understanding, cross-scenario generalization, and continuous learning from production-line feedback are realized to further improve the detection accuracy and adaptability.
The 3D AI AOI equipment provides an efficient and accurate solution for the inspection of aluminum die-castings in automotive parts with advanced technology.
Quantitative results: After practical application, the 3D AI AOI equipment has achieved remarkable results. The detection rate has increased to 96%, and the miss-detection rate has decreased to < 4%, effectively reducing the risk of defective products flowing into subsequent processes. The false-alarm rate has been reduced by -70%, greatly reducing the workload of manual re-inspection and improving production efficiency. The model-changing time has been shortened to 5min, meeting the production demand for rapid model-changing and improving the flexibility of the production line.
FAQ
How small porosity defects can the 3D AI AOI equipment detect?
The 3D AI AOI equipment has a micron-level detection accuracy and can detect micron-level porosity and inclusion defects inside aluminum die-castings, effectively ensuring product quality.
How many samples are needed for programming when using this equipment?
Using the DaoAI AI AOI software system and APDT positive-sample/few-sample learning, only 1-20 good products are required. Zero - code automatic programming can be completed in 5 minutes with one good product.
What's the efficiency of the equipment's model-changing?
The model-changing time of this equipment can be shortened to 5min, meeting the production demand for rapid model-changing and greatly improving the flexibility and production efficiency of the production line.