T-shaped fillet seam tracking method based on laser stripe visual sensor

KONG Meng; ZHANG Jie; ZHANG Lunzhao; HOU Zhen; CHEN Huabin; CHEN Shanben

Views : 0 下载量: 372 CSCD: 13

Export
Share
Collection
Album

T-shaped fillet seam tracking method based on laser stripe visual sensor
Vol. 48, Issue 10, Pages: 101-104(2018)
Published：2018
DOI：
稿件说明：

移动端阅览

DOI：

KONG Meng, ZHANG Jie, ZHANG Lunzhao, et al. T-shaped fillet seam tracking method based on laser stripe visual sensor[J]. Eletric Welding Machine2018, 48(10): 101-104. DOI：

摘要

针对T型接头角焊缝机器人GMAW跟踪

自主研制了一套激光视觉传感器和滤光系统。基于矩阵转换形式的测量原理

简化了视觉系统标定。利用Hessian矩阵的Steger方法提取T型接头角焊缝激光条纹图像线特征及其方向信息

并使用随机抽样一致算法进行形貌直线的拟合

获取了焊缝中心特征点。跟踪试验结果表明

焊缝左右和高度方向的平均误差为0.52

满足机器人实际焊接生产要求。

Abstract

Aimed at seam tracking of fillet weld for robotic welding

we developed laser vision sensor and filter system in this paper. Based on measuring principle of matrix transformation

it simplified calibration of vision system. Steger method based on Hessian matrix is used to extract sub-pixel level linear feature and its orientation information. The random sample consensus algorithm is used to fitting lines as profile model and center of weld seam is extracted furtherly. Tracking test results shows that mean tracking error is 0.52 along welding direction

which meets the actual welding production requirements of the robot.