Deep learning detects welding joint defects using images and sound
Explainable Temporal Attention-based Defect Detection For Fillet Joints in Real-Time Gas Metal Arc Welding Based on Multi-modal Data
Artificial IntelligenceMachine Learning
Summary
Welding can create tough-to-see defects that cause problems later. To catch these defects early, the authors created a computer program that looks at both welding pictures and sounds to find issues like holes or weak spots. Their system pays special attention to important parts of the data, which helped it find problems very accurately. They also used tools to explain how the program makes decisions, so users can understand why it thinks something is wrong. This makes it easier to trust the program when checking welding quality in real time.
deep learningtemporal attentiondefect detectionGas Metal Arc Weldingfillet jointsmulti-modal datasound spectrogramexplainable AIF1 score
Authors
Mobina Mobaraki, Mahyar Asadi, Klaske Van Heusden, Guy A. Dumont
Abstract
Deep learning is an efficient technique to monitor the real time welding process, reducing post-welding repairs and production delays. This paper leverages the monitoring capability by proposing a multi modal temporal attention based deep learning defect detection model for internal defects that are challenging to detect, including porosity, lack of penetration and fusion, undercut, and cold lap during Gas Metal Arc Welding in fillet joints. The model is trained on collected welding images and sound data from an industrial collaborative welding robot. The results show that the attention module can improve the F1 Score to 0.99. We use explainable Artificial Intelligence to interpret the proposed models behavior and dataset distribution, determining potential important areas in image and sound spectrograms and preferred modality to detect each defect. This improves trust and reliability in Artificial Intelligence driven welding inspection.