基于变分立体匹配算法的GMAW熔池形貌三维重建
Three-dimensional reconstruction of GMAW weld pool ap-pearance based on variational stereo matching algorithm
梁志敏 1高旭 2任政 2武子琴 2王立伟 1汪殿龙1
作者信息
- 1. 河北科技大学,材料科学与工程学院,石家庄, 050000;河北省材料近净成形技术重点实验室,石家庄, 050000
- 2. 河北科技大学,材料科学与工程学院,石家庄, 050000
- 折叠
摘要
为实现完整熔池表面形貌三维传感,构建了双棱镜单摄像机立体视觉传感系统.针对熔池图像纹理缺乏造成的立体匹配困难的问题,引入了全局优化的变分立体匹配算法,通过建立包含灰度差异数据项和空间连续性约束项的能量函数的可行性泛函,经过迭代求解获得具有丰富细节的熔池表面稠密视差图.对自制非标准凹面形状进行立体匹配和三维重建,结果表明,宽度误差小于 3.16%,深度误差小于 4.82%.基于该算法实现了熔化极气体保护焊(gas metal arc welding,GMAW)的堆焊及V形坡口对焊条件下,不同熔透状态熔池稠密视差图计算和表面形貌的三维重建.
Abstract
In order to realize the complete three-dimensional sensing of weld pool surface morphology,a stereo vision sens-ing system with biprism and single camera was constructed.Aiming at the difficulty of stereo matching caused by the lack of texture in weld pool map,a globally optimized variational stereo matching algorithm was introduced.By establishing the feasibility function of energy function containing gray differ-ence data item and spatial continuity constraint item,the dense disparity figure of weld pool surface with rich details was ob-tained through iterative.The results of stereo matching and three-dimensional reconstruction of the self-made non-stand-ard concave shape show that the width error is less than 3.16%and the depth error is less than 4.82%.Based on this al-gorithm,the dense disparity map of weld pool surface is calcu-lated and reconstructed under the conditions of bead on plate and V-groove butt welding with different penetration states.
关键词
熔池形貌/三维重建/变分立体匹配算法/熔化极气体保护焊Key words
weld pool appearance/three-dimensional re-construction/variational stereo matching algorithm/gas met-al arc welding引用本文复制引用
基金项目
国家自然科学基金资助项目(51875168)
河北省自然科学基金资助项目(E2020208089)
出版年
2024
NETL
NSTL
万方数据