利用“半径—深度”算法和空间投影关系的焊缝定位方法  

Active vision sensing method for weld location by“circle-depth relation” algorithm

作　　者：徐培全[1] 唐新华[1] 姚舜[1] 俞海良[1] 

机构地区：[1]上海交通大学材料科学与工程学院,上海200030

出　　处：《焊接学报》2006年第10期45-48,共4页Transactions of The China Welding Institution

基　　金：国际科技合作重点项目-船舶大功率激光建造技术(2004DFA02400)

摘　　要：提出了三个重要的角度来描述被测焊缝三维信息。在此基础上,构建了基于“半径—深度”算法和空间投影关系的深度恢复模型。研究了GTAW焊接条件下焊缝深度信息与离轴角之间的关系。并对焊缝特征点进行了识别与定位。并用均方误差(MSE)对恢复精度进行了比较。结果表明,利用提出的深度恢复算法,实现了对接焊缝与斜坡焊缝的深度恢复,获得了满意的结果;视觉传感器的焊缝定位精度具有高效率、高精度的特征,具有较理想的发展前景。Three vital angles were put forward, so the weld could be described by three-dimensional information. On this basis, mathematical model of depth recovery according to 'circle-depth relation' algorithm and projection rules was constructed. The relation ship between depth values and off-axis angle γ under gas tungsten arc welding experiment condition was addressed by real experiment and the characteristic points of weld was described and located.Mean square error was used to analyze the recovery precision. The results showed: (1) Depth recovery for butt joint and ramp welded seams realized; (2) Weld can be located very well by using proposed vision sensor based on circular laser trajectory; and proposed vision sensor manifested a promising result with high precision and high efficiency.

关 键 词：激光锥体投影 环形激光轨迹 深度恢复 焊缝定位 

分 类 号：TG409[金属学及工艺—焊接]