Abstract
The threeÂ-dimensional weld pool top surface shape provides important informaÂtion about the state of weld penetration during welding. In this study, a method was developed to quantitatively relate weld pool surface height to the reversed electrode image (REI) on the weld pool surface. This new feature was extracted from the weld pool image using a passive vision-Âbased monitoring system during gas tungsten arc welding (GTAW). Due to the specular reflection of the weld pool top surface, the REI is visible on the weld pool surface during GTAW. The position of the REI was determined with a robust image processing algorithm. Based on the principle of light reflection, the distance between the electrode tip and the REI (DERI) was related to the weld pool surface height. By assuming the weld pool surface was a spherical mirror, a reflection model was established to calculate the surface height (SH) index based on the measurement of the DERI, arc length, and weld pool geometry. The proÂposed method was verified with beadÂ-onÂplate welding experiments. The SH was positively related to the face reinforcement or depression of the weld bead. This method was applied to monitor the penetration state during beadÂonÂplate autogeÂnous welding, particularly when a complete penetration weld was formed.