To solve the current problem of poor weld formation due to groove width variation in swing arc narrow gap welding, an infrared passive visual sensing detection approach was developed in this work to measure groove width under intense welding interferences. This approach, called global pattern recognition, includes self-adaptive positioning of the ROI window, equal division thresholding and in situ dynamic clustering algorithms. Accordingly, the self-adaptive positioning method filters several of the nearest values of the arc’s highest point of the vertical coordinate and groove’s same-side edge position to determine the origin coordinates of the ROI window; the equal division thresholding algorithm then divides and processes the ROI window image to extract the groove edge and forms a raw data distribution of groove width in the data window. The in situ dynamic clustering algorithm dynamically classifies the preprocessed data in situ and finally detects the value of the groove width from the remaining true data. Experimental results show that the equal division thresholding algorithm can effectively reduce the influences of arc light and welding fume on the extraction of the groove edge. The in situ dynamic clustering algorithm can avoid disturbances from simulated welding spatters with diameters less than 2.19 mm, thus realizing the high-precision detection of the actual groove width and demonstrating stronger environmental adaptability of the proposed global pattern recognition approach.

In order to gain a deeper understanding of the distribution of residual stresses in swing-arc narrow-gap GMA welding, this paper comprehensively considers the arc motion trajectory and joint geometry and establishes a three-dimensional finite element numerical analysis model for residual stresses based on elastic–plastic theory. Using the Ansys software, the welding residual stresses were calculated under swing frequencies of 4 Hz, 3 Hz, and 2 Hz, and the distribution characteristics of residual stresses were analyzed. The results indicate that the model effectively and accurately represents the movement trajectory and distribution characteristics of the swing arc. Furthermore, the calculated temperature field and residual stress outcomes align closely with the experimental findings, thereby validating the accuracy of the model. Under varying swing frequencies, the distribution patterns of residual stress along each sampling line exhibit a consistent similarity. The residual stress is predominantly concentrated in the weld zone and the adjacent heat-affected zone, while it remains relatively low in areas further away from the weld. As the swing frequency increases, the residual stress decreases. The reason for this is that an increase in swing frequency can lead to a more uniform distribution of arc heat within the weld bead, ultimately resulting in lower residual stress.