In the automotive manufacturing field, the surface quality of stamped sheet metal is crucial. WeLinkirt's AI vision technology provides an effective solution to the problem of detecting 0.3mm surface defects.
User Scenario: A leading automobile parts manufacturer's stamping sheet metal production line mainly produces various types of automobile stamping sheet metal parts. The detection object is the surface of the stamping sheet metal with a thickness of 0.3mm, and it is necessary to detect tiny defects such as scratches, pits, and cracks to ensure that the products meet the high-quality requirements of automobile manufacturing.
Pain Points: Traditional detection methods face many difficulties in this scenario. Manual inspection is inefficient, with only about 30 products being inspected per hour, and the missed detection rate is as high as 15%, which is difficult to meet the needs of large-scale production. At the same time, the false alarm rate of manual inspection is about 20%, resulting in a large number of products needing re-inspection, which increases production costs and time. In addition, when changing the production line model, it takes about 30 minutes to manually readjust the detection standards and processes, seriously affecting the production rhythm.
Technical Principles
WeLinkirt uses advanced AI algorithms and imaging technologies to solve the above problems. In terms of algorithms, deep learning algorithms are used to learn and train a large number of stamping sheet metal surface images. Through the convolutional neural network (CNN), the feature information of the images is extracted, which can accurately identify different types of surface defects. In terms of imaging, the self-developed 3D camera can obtain the three-dimensional topography information of the sheet metal surface. Combined with the three-dimensional topography reconstruction technology, the three-dimensional features of tiny defects can be clearly presented, improving the accuracy of detection. The combination of this algorithm and imaging technology is effective because the deep learning algorithm has a strong feature learning ability and can extract representative features from complex images, while the 3D camera and three-dimensional topography reconstruction technology provide more comprehensive surface information, making up for the deficiencies of traditional 2D detection.
- The deep learning algorithm can automatically adjust model parameters through learning a large number of images to adapt to different defect features and image backgrounds.
- The 3D camera can obtain the depth information of the object surface and can accurately detect some tiny defects hidden under the surface.
- The three-dimensional topography reconstruction technology processes and analyzes the point-cloud data obtained by the 3D camera to generate an intuitive three-dimensional model, which is convenient for inspectors to make judgments.
- Through semantic understanding and cross-scenario generalization ability, the model can quickly adapt and be applied in different stamping sheet metal products and production environments.
WeLinkirt's Solutions and Product Introduction
WeLinkirt provides the DaoAI AI AOI software system and the DaoAI 2D / 3D AI AOI equipment. The DaoAI AI AOI software system has the feature recognition ability of the visual basic model. With only 1-20 good samples, through APDT positive-sample/few-sample learning, 0-code automatic programming can be realized within 5 minutes. At the same time, it can also perform semantic false-alarm filtering to effectively reduce the false-alarm rate. The DaoAI 2D / 3D AI AOI equipment uses the self-developed 3D camera and three-dimensional topography reconstruction technology, which can detect hidden solder joints, coplanarity, and micron-level topography, and the detection accuracy for 0.3mm surface defects can reach the micron level. During the implementation process, the equipment is installed on the stamping sheet metal production line to conduct online inspection of products. The software system analyzes and processes the inspection data in real-time and feeds the results back to the production line control system.
WeLinkirt's solution provides an efficient and accurate means for the detection of surface defects in automobile stamping sheet metal.
Quantitative Results: After adopting WeLinkirt's solution, the inspection efficiency has been greatly improved, with about 120 products being inspected per hour, a three-fold increase. The missed detection rate has been reduced to <0.6%, and the false-alarm rate has been reduced by -63%, effectively reducing the re-inspection workload. The production line model change time has been shortened from 30 minutes to 5 minutes, significantly improving the flexibility and efficiency of production.