You have attempted to access the full-text of an Early Posting article. Access is available via an institutional subscription.
See the Early Posting FAQ page for additional information.
See the Early Posting FAQ page for additional information.
Vision-based algorithm for on-line TIG welding deviation detection of stainless steel welded pipes
JOSA A- received 10/17/2023; accepted 04/26/2024; posted 04/26/2024; Doc. ID 509496
- Abstract: Tungsten inert gas (TIG) welding is the main welding process in the production ofstainless steel welded pipe. According to the morphological characteristics of the weldingmolten pool image during the TIG welding process of stainless steel welded pipes, the exactposition of the tungsten needle tip is calculated using image moments. Extract the weld regionin the contour of the molten pool, interpolate the contour curve based on the cubic B splinecurve interpolation method, utilize the characteristics of the S-G filter, remove the interferencecoordinates in the contour curve through the de-trending of the contour curve, extract the weldfeature points, and realize the accurate identification of weld seams. The experimental resultsshow that the method can accurately calculate the welding deviation in the welding process.