A Welding Defect Detection Model Based on Hybrid-Enhanced Multi-Granularity Spatiotemporal Representation Learning

• Published in: Sensors (Basel, Switzerland) Vol. 25; no. 15; p. 4656
• Main Authors: Shi, Chenbo, Yan, Shaojia, Wang, Lei, Zhu, Changsheng, Yu, Yue, Zang, Xiangteng, Liu, Aiping, Zhang, Chun, Feng, Xiaobing
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 27.07.2025; MDPI
• Subjects: Accuracy; Cameras; Decision making; Deep learning; Defects; image interference; key interference-free frames; Methods; Morphology; multi-granularity spatiotemporal features; porosity defect; Vision systems; key interference-free frames; deep learning; porosity defect; image interference; multi-granularity spatiotemporal features

Real-time quality monitoring using molten pool images is a critical focus in researching high-quality, intelligent automated welding. To address interference problems in molten pool images under complex welding scenarios (e.g., reflected laser spots from spatter misclassified as porosity defects) an...