AI AOI Software System Enables Defect Detection on Textured Surfaces of Chemical Materials

In the current industrial development trend, industrial AI has become a key force in improving the level of intelligent manufacturing. WeLinkirt's AI AOI software system plays an important role in unsupervised anomaly detection on textured surfaces in the chemical/materials industry.

User Scenario: In the chemical/materials industry, a leading manufacturer's production line mainly produces chemical materials with textured surfaces. These materials are widely used in various fields such as construction and automotive. In the production process, it is necessary to detect defects on the textured surfaces of the materials to ensure that the product quality meets the standards. The detection objects include various abnormal situations such as surface scratches, holes, and impurities.

Pain Points: Traditional detection methods face many difficulties when dealing with defect detection on the textured surfaces of chemical materials. On the one hand, manual detection is inefficient, with each detection cycle taking up to several hours, and the labor cost is high. At the same time, the missed detection rate of manual detection is as high as 5%, and the false alarm rate also reaches 8%, which is difficult to meet the requirements of high-quality production. In addition, with the increase in product types, the problem of long change-over time has become more prominent, seriously affecting production efficiency. In the general trend of industrial AI development, traditional detection methods can no longer meet the needs of efficient defect detection in industrial visual quality inspection, which restricts the improvement of the intelligent manufacturing level.

Technical Principle

WeLinkirt's AI AOI software system uses advanced feature recognition technology based on a visual foundation model. This technology can accurately identify various features of the textured surface through in - depth analysis of images. The core lies in using a large amount of image data for training, so that the model can learn the characteristic patterns of normal textures. During the detection process, the real-time collected images are compared with the learned normal patterns, and once a difference is found, it is judged as a possible anomaly.

• The feature recognition technology of the visual foundation model can analyze images from multiple dimensions, including texture direction, density, and grayscale, so as to achieve precise detection of small defects.
• The APDT positive-sample/few-sample learning method can quickly learn the features of normal textures with only 1-20 good samples, greatly reducing the time and cost of sample collection.
• The semantic false-alarm filtering mechanism can perform secondary screening on the detection results, removing false alarms caused by environmental interference and other factors, and improving the detection accuracy.

WeLinkirt's Solution and Product

WeLinkirt's AI AOI software system is the core to solve the problem of defect detection on the textured surfaces of chemical materials. This system has unique capabilities: First, it supports 0-code automatic programming for a good sample in 5 minutes, greatly shortening the programming time and improving the detection efficiency. Second, through APDT positive-sample/few-sample learning, the model can be trained with only a small number of good samples, quickly adapting to the detection of different types of materials. The semantic false-alarm filtering function effectively reduces the false-alarm rate and improves the reliability of detection. In addition, the system supports 100% local private deployment of SDK/API/Docker, ensuring data security and meeting the enterprise's requirement of keeping data in - house. At the same time, WeLinkirt's DaoAI 2D/3D AI AOI equipment can be used as a supporting device to provide more accurate image data for detection.

The AI AOI software system brings an efficient and accurate solution for defect detection on the textured surfaces of chemical materials.

Quantitative Results: After applying WeLinkirt's AI AOI software system, the detection effect of the manufacturer has been significantly improved. The detection rate has reached 98%, and the missed-detection rate has been reduced to <2%, greatly improving the product quality. The false-alarm rate has been reduced by -65%, reducing unnecessary reinspection work. The change-over time has been shortened from several hours to 5min, greatly improving the production efficiency.