Seam-tracking technology based on vision sensing is the key technology to realize robot intelligent welding. Because of changes in the weld gap, the diversity of workpiece material and surface conditions, and the interference of welding noises, it is extremely difficult for the robot to realize real-time seam-tracking in gas metal arc welding (GMAW) of large structures. So, a method of position detection and weld gap feature extraction is proposed for GMAW seam-tracking system of fillet weld with variable gap. This method established a highly robust weld feature extraction model based on a low-cost structured-light vision sensor. In this model, using the reflection characteristic of the stripes on fillet weld, a feature extraction method for variable gap weld based on column gray difference operator was proposed. To overcome the interference of welding noises, this model adopted the AND logic operation method between adjacent sampled images. To overcome the interference of uneven and strong reflection conditions, an optimized random sampling consistency (RANSAC) algorithm was proposed and used for weld feature extraction. The optimized RANSAC algorithm used the linear slope of the stripes to optimize the random sampling process of the algorithm. The experimental results showed that the average detection errors of the proposed method in the Y-axis and Z-axis directions are 0.19 mm and 0.23 mm, respectively, at a welding speed of 1000 mm/min. The proposed method could realize seam tracking of the variable gap fillet weld and still had good robustness under the uneven and strong reflection of the workpiece surfaces.
Three-dimensional (3D) zigzag-line welding seams are found extensively in the manufacturing of marine engineering equipment, heavy lifting equipment, and logistics transportation equipment. Currently, due to the large amount of calculation and poor real-time performance of 3D welding seam detection algorithms, real-time tracking of 3D zigzag-line welding seams is still a challenge especially in high-speed welding. For the abovementioned problems, we proposed a method for the extraction of the pose information of 3D zigzag-line welding seams based on laser displacement sensing and density-based clustering point cloud segmentation during robotic welding. after thee point cloud data of the 3D zigzag-line welding seams was obtained online by the laser displacement sensor, it was segmented using theρ-Approximate DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm. In the experiment, high-speed welding was performed on typical low-carbon steel 3D zigzag-line welding seams using gas metal arc welding. The results showed that when the welding velocity was 1000 mm/min, the proposed method obtained a welding seam position detection error of less than 0.35 mm, a welding seam attitude estimation error of less than two degrees, and the running time of the main algorithm was within 120 ms. Thus, the online extraction of the pose information of 3D zigzag-line welding seams was achieved and the requirements of welding seam tracking were met.