Bo Yang

Vision-based weld seam extraction poses a significant challenge for weldments with complex spatial structures in automated welding. Existing research primarily focuses on identifying weld seams from weldments with given positions and postures, while practical weld path planning requires multiple weld seams identified within arbitrarily placed weldments. This paper proposes a methodology that identifies weld seams from arbitrarily placed spatial planar weldments in a single run. First, by introducing a turntable calibrated with respect to a 3D camera, we perform 3D reconstruction on an arbitrarily placed spatial planar weldment. Second, an improved RANSAC algorithm based on Euclidean clustering is proposed to carry out plane segmentation, focusing on segmentation accuracy. Finally, we present a novel weld seam extraction algorithm leveraging the half-edge data structure to efficiently compute weld seams from the segmented planes. The experiments conducted in this study demonstrate that the average segmentation errors (as an indirect indicator of weld seam extraction error) are reduced by 90.3% to 99.8% over conventional segmentation methods, and the standard deviations are reduced by 64.8% to 97.0%.

Turntables play an essential role in various industrial areas due to their ability to improve the degree of freedom of workpieces or tools. In applications where positional accuracy of the objects is required, the accuracy of the system parameters of the turntable is critical for the applications to work properly. This paper proposes a new approach to calibrating the turntable system. First, we propose an optimized RANSAC (random sample consensus) algorithm to obtain high-accuracy reference planes from multiple frames of point clouds grabbed from the reference object placed on a turntable. Second, an singular value decomposition-based two-step method is proposed to calculate the rotation axis vector and the center position of the turntable based on the reference planes extracted by the modified RANSAC algorithm. Finally, several experiments are performed to verify the proposed methods. Compared with the existing methods, our approach gets the analytical results and tries to correct the rotation angles. The experimental results show that the proposed method considerably improves calibration accuracy and efficiency without complex devices.