A precise seam tracking method for narrow butt seams based on structured light vision sensor

At present, most popular approaches of seam detection are based on structured light vision sensors owing to features of high accuracy and robustness. However, the deformation of laser stripe is not obvious enough when it is projected onto narrow butt seam, whose width is less than 0.2 mm, so the traditional structured light vision sensor cannot detect the seam feature of narrow butt seam. In this paper, a precise seam tracking method for narrow butt seams based on structured light vision sensor is proposed. Firstly, a new structured light vision sensor with optical filters and an extra LED light is developed to filtered out most of noises from strong arc lights and acquire the image including laser stripe and narrow butt seam. In addition, an image processing method for the vision sensor is designed to obtain welding torch deviations of narrow butt seams both in horizontal and vertical directions. Based on the obtained deviations, two independent Fuzzy-PID controllers are designed to achieve seam tracking control accurately. Finally, in order to verify the effectiveness of the proposed method in this paper, a welding experimental system is setup and welding experiments are carried out. Experimental results demonstrate that this method can meet the requirement of narrow butt seams tracking accuracy.