In the automotive manufacturing industry, the quality inspection of resistance spot welding nuggets is of crucial importance. DaoAI, with its advanced AI vision technology, provides efficient and precise inspection solutions for automotive and component manufacturers.
User Scenario: A leading automotive component manufacturer's resistance spot welding production line. The main products are automotive body structural components, and the inspection object is the resistance spot welding nugget. In the automotive manufacturing process, resistance spot welding is a commonly used joining process. The quality of the welding nugget directly affects the strength and safety of the body structural components. Therefore, the quality inspection of the welding nugget is a key link in this process.
Pain Points: Traditional inspection methods have many quantitative dilemmas. Manual inspection is inefficient, with a long inspection time for each welding spot, resulting in a slow production line rhythm and high labor costs. Moreover, manual inspection is prone to missed detections and false alarms. The missed detection rate is about 3%, and the false alarm rate is as high as 15%. This not only affects product quality but also increases the re-inspection volume. In addition, traditional 2D optical inspection methods have blind spots and cannot accurately obtain the 3D morphology information of the welding nugget. It is difficult to detect some welding spots hidden under the package, which cannot meet the strict quality compliance requirements.
Technical Principle
DaoAI uses self-developed 3D cameras and three-dimensional morphology reconstruction technology to solve the above problems. The self-developed 3D camera can emit special structured light. By analyzing the information of the reflected light, it can accurately obtain the three-dimensional morphology data of the welding nugget. The three-dimensional morphology reconstruction algorithm reconstructs the real 3D model of the welding nugget based on these data. This method is effective because it breaks through the limitations of 2D optical inspection and can capture the feature information of the welding nugget in all directions. By obtaining the 3D morphology of the welding nugget, we can more accurately judge the quality of the welding spot, such as the size, shape, and depth of the welding nugget, thus greatly improving the accuracy of the inspection.
- Structured light coding: Through a special coding method, the camera can more accurately parse the information of the reflected light, thereby improving the accuracy of 3D data collection.
- Multi - view fusion: The welding nugget is photographed from multiple angles, and then the 3D data from different views are fused to obtain a more complete and accurate 3D model.
- Deep learning algorithm: A deep learning algorithm is used to analyze the reconstructed 3D model and identify various defect features of the welding nugget, such as cracks and holes.
DaoAI Solution and Product Introduction
DaoAI provides the DaoAI 2D / 3D AI AOI equipment and the DaoAI AI AOI software system. The DaoAI 2D / 3D AI AOI equipment integrates self-developed 3D cameras and three-dimensional morphology reconstruction technology, which can quickly and accurately obtain the 3D morphology information of the welding nugget. This equipment features high precision and high speed, suitable for large-scale production inspection. The DaoAI AI AOI software system is based on the feature recognition of the visual basic model, supports 0-code automatic programming for a good product in 5 minutes, uses APDT positive-sample/few-sample learning (only 1-20 good products are needed), and has the function of semantic false-alarm filtering. In the implementation, first, the DaoAI 2D / 3D AI AOI equipment is used to collect 3D data of the welding nugget, and then the collected data is transmitted to the DaoAI AI AOI software system for analysis and processing. The software system quickly determines whether the welding nugget has defects according to the preset inspection rules and outputs the inspection results.
DaoAI's AI vision solution brings new breakthroughs to the inspection of resistance spot welding nuggets in the automotive industry, effectively improving the inspection efficiency and accuracy.
Quantitative Results: After adopting DaoAI's solution, the inspection effect has been significantly improved. The detection rate has increased from about 97% to 99.2%, and the missed detection rate has been reduced to < 0.8%. The false alarm rate has been reduced by -68%, greatly reducing the re-inspection volume. At the same time, the change-over time has been shortened from 30 minutes to 5min, improving the flexibility and production efficiency of the production line.