Groove-center detection in gas metal arc welding using a template-matching method. Issue 9 (October 2016)

• Record Type: Journal Article
• Authors: Wang, Xiaojia; Shi, Yonghua; Yu, Guoqing; Liang, Bin; Li, Yang
• Is Part Of: International journal of advanced manufacturing technology. Volume 86:Issue 9/12(2016)
• Page Start: 2791
• Page End: 2801
• Publication Date: 2016-10
• Subjects: Image processing -- Template matching -- Seam tracking -- High-dynamic-range camera -- Gas metal arc welding; Manufacturing processes -- Periodicals; Production engineering -- Periodicals; 670.427
• DOI: 10.1007/s00170-016-8389-7
• Languages: English
• ISSNs: 0268-3768

Abstract

Abstract To achieve welding automation, the center of the groove needs to be detected accurately during welding. We developed a method based on template-matching to detect the groove center during gas metal arc welding (GMAW). To avoid the negative influence of the strong GMAW arc light, a high-dynamic-range camera was used to capture details of the welding arc, molten pool, and the V-groove simultaneously in a single image. Two image-processing and object-detection algorithms were developed to detect the center of the welding pool and the groove based on template matching. The experimental results of the latter algorithm were more accurate for identifying the position of the groove center. However, interference in the welding process caused the template-matching method to fail under certain conditions. Therefore, the two detection algorithms were combined to improve the detection accuracy. After filtration of the detected welding-pool center, the groove-center detection algorithm based on template matching results in higher accuracy.