基于三角剖分和轮廓分析的船舶焊缝特征识别

为了实现船舶焊接件数字模型中焊缝特征的精确识别,进而提高焊接机器人焊接工艺选择的快速性和准确性,提出了基于三角剖分和轮廓分析的焊缝特征识别算法。首先通过角系数法判断多边形的凹凸顶点,基于凹顶点和三角形旋向的Delaunay三角剖分,构造三维模型表面的三角形网格并生成STL文件；然后基于相邻三角面片的法向量夹角,提取出模型的轮廓线及点；最后根据接头空间位置和最小轮廓线距离识别出焊接接头和坡口形状。测试结果表明,基于三角形旋向的网格剖分适用于如“梳子”等复杂多边形,与其他相关方法相比,其网格平均和关联质量系数分别平均增加12.06%和12.26%,有效降低了畸形三角形的产生并提高了网格质量,而融合轮廓分析后不仅能实现4类接头及10种坡口的焊缝特征识别,而且具有高效、高准确率优势,从而验证了算法的有效性。

Feature Recognition of Ship Welding Seam Based on Triangulation and Contour Analysis

In order to realize the accurate identification of weld features in the digital model of ship welded parts, and to improve the speed and accuracy of welding process selection of welding robots, a weld seam feature recognition algorithm based on triangulation and contour analysis is proposed. First, the concave and convex vertices of the polygon are judged by the angle coefficient method, and based on the Delaunay triangulation of the concave vertices and the triangle rotation, the triangle mesh of the 3D model surface is constructed and the STL file is generated. Second, based on the normal vector angles of adjacent triangles, the contours and points of the model are extracted. Finally, the welding joint and groove shape are identified according to the joint space position and the minimum contour line distance. The test results show that the mesh division based on the triangle rotation is suitable for complex polygons such as "combs", compared with other related methods, the factors of grid average and associated quality are increased by an average of 12.06% and 12.26% respectively, which effectively reduces the generation of deformed triangles and improves the quality of the mesh. Furthermore, after the meshing and contour analysis are merged, 4 types of joint forms and 10 types of groove weld features can not only be identified, but also the recognition efficiency is high and the recognition accuracy is good, which verifies the effectiveness of the proposed algorithm.