This paper discussed seam tracking technology by computer vision sensing in real time for robot GTAW. An image processing algorithm was presented to extract the seam trajectory and the offset of the torch to the seam in the welded pool images of aluminum alloys with grooves. Also the tracking sequence was analyzed and designed. C++ computer language was used to realize the algorithm. The experimental results showed that the error of real-time image process could meet the requirement of production. Such an algorithm was proved to be feasibility in factual manufacturing.
展开▼
机译：本文通过实时对机器人GTAW实时感应的计算机视觉传感缝制跟踪技术。提出了一种图像处理算法以提取焊缝轨迹和焊炬的焊缝偏移在铝合金的焊接池图像中的接缝。还分析和设计了跟踪序列。 C ++计算机语言用于实现算法。实验结果表明，实时图像过程的误差可以满足生产的要求。证明了这种算法在事实制造中是可行性的。
展开▼
