Quality control of laser welds based on the weld surface and the weld profile

2D or 3D sensor technology can be used for data acquisition to monitor the weld quality during laser welding. Compared to a 2D camera image, the 3D height data contains additional relevant information for quality inspection. However, the disadvantages are system complexity, higher costs, and longer acquisition times. Therefore, we compare two image-based methods with the quality assessment based on height data. The
first method uses feature vectors of coaxial acquired grayscale images. The significant advantage is that a camera is often integrated into the laser system, so no additional hardware is required. In the second approach, we use an AI-based single-view 3D reconstruction method. The height profile is calculated from
a camera image and used for further quality assessment. Thus, we combine the advantages of 2D data acquisition with higher accuracy in evaluating 3D data. In this paper, we analyze a dataset of welded hairpins with different defect types and compare the quality assessment using the height data acquired with OCT, the feature vectors from the camera images, and the reconstructed height data.