摘要
针对高效鲁棒的焊缝识别对于提高焊接质量和效率具有重要的作用,提出了一种基于线结构光的薄壁件窄焊缝快速识别方法。首先,对激光照射的焊缝图像进行去噪和增强;其次,分别利用Ransac算法和最小二乘法对焊缝和激光条纹进行直线拟合;接着,以二直线交点为中心建立ROI,连接ROI中的连通体获得修正后的交点;最后,对修正后的交点加以平移,以斜率为状态变量进行卡尔曼滤波,以修正后的交点为中心建立ROI并计算ROI中各点斜率,寻找具有最接近滤波后的斜率的点,将其反向平移后的坐标作为交点的最终值。实验证明该算法具有较高的鲁棒性和较快的处理速度,可满足窄焊缝的实时识别需求。
Efficient and robust weld identification plays an important role in improving welding quality and efficiency.In this paper,a fast identification method for narrow welds of thin-walled parts based on line structured light is proposed.Firstly,the weld image irradiated by laser is denoised and enhanced.Then,RANSAC and least square methods were used to fit the weld seam and laser fringe.Then,the ROI was established centered on the intersection point of two lines,and the modified intersection point was obtained by connecting the connecting body in the ROI.Finally,the modified intersection point is translated,and the slope is used as the state variable to carry out Kalman filtering.The point with the most similar slope is found near the modified intersection point,and the coordinate of the point after the reverse translation is taken as the final value.In the experiment,the gray gravity center method is used to establish the reference data,and the identification accuracy is statistically analyzed.Experiments show that the algorithm has high robustness and fast processing speed,which can meet the real-time identification requirements of narrow weld.
作者
徐子恒
夏仁波
赵吉宾
张天宇
陈月玲
XU Zi-heng;XIA Ren-bo;ZHAO Ji-bin;ZHANG Tian-yu;CHEN Yue-ling(State Key Laboratory of Robotics,Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,China;Institutes for Robotics and Intelligent Manufacturing,Chinese Academy of Sciences,Shenyang 110016,China)
出处
《组合机床与自动化加工技术》
北大核心
2022年第2期50-53,58,共5页
Modular Machine Tool & Automatic Manufacturing Technique
基金
国家重点研究计划项目(2018YFB1107803)。
