Weld pool image centroid algorithm for seam tracking in arc welding process

Abstract

Seam tracking performance of an arc welding system is crucial to achieve high-quality welds. Visual sensing is one of the most attractive approaches to detect the seam position in the welding process, which provides valuable information to control the arc following the expected path. However, it is difficult to accurately detect the seam position adjacent to weld pool due to strong light disturbance. Unlike most seam detection methods, a novel algorithm based on weld pool image centroid is presented, which can detect the deviations between the arc tip and seam centerline. The weld pool images are captured by a camera arranged ahead of a welding torch. Image processing techniques are employed to analyze the features of weld pool and its surroundings, and the centroid of weld pool image is extracted as a parameter for seam tracking. It is worth to note that the centroid corresponds with gray and thermal distribution of weld pool affectted by the deviations between the arc tip and the seam centerline, which indicates the presence of relationship between the centroid and the deviations. Therefore, the deviations between the arc tip and seam centerline can be estimated by this centroid. To establish this centroid algorithm, the least square linear regression method is applied to correlate the relationship between the centriod and the deviations under different welding conditions. As compared with directly detecting the seam position, the centroid can be measured and computed easily. This algorithm is expected to provide a promising practical approach to improve the accuracy of seam tracking in real time, and subsequently to ensure the welding quality.