基于视觉传感的CO_2焊焊接偏差识别

Vision-Based Welding Deviation Detection for CO_2 Arc Welding

高质量焊接图像的获取和焊接偏差信息的获取是焊接偏差检测中的两个重要步骤.文中在对CO_2焊的成像特征进行分析的基础上,采用宽动态范围相机采集清晰和稳定的CO_2焊实时图像,并根据焊接图像的特点,开发了一种改进的Canny算法来获得边缘信息,结合Hough变换和先验知识提取出坡口边缘;为了拟合出熔池边缘,提出一种基于条件约束的差分进化(Differential Evolution,DE)椭圆识别算法;在此基础上计算得到焊接偏差;并通过试验对焊接偏差识别算法的鲁棒性和精确性进行验证.结果表明:文中提出的算法可满足焊缝跟踪和焊接自动化的要求.

Capturing high-quality welding images and extracting deviation information are two important steps ofwelding deviation detection. In this paper, on the basis of imaging characteristics analysis in the process CO2 arcwelding, real-time welding images were acquired clearly and steadily by using a wide dynamic range camera.Then, according to the characteristics of welding images, an improved Canny algorithm was developed to detectgroove edges, and both Hough transform and prior knowledge were used to connect these edges. Moreover, in orderto fit out the edge of weld pool, a differential evolution ellipse detection algorithm on the basis of condition restrictionwas proposed, with which welding deviation can be successfully calculated. Experimental results show that theproposed algorithm possesses strong robustness and high precision, so that it meets the requirements of seam trackingand welding automation well.