aiqbench analysis
This research presents a multi-modal deep learning model using temporal attention mechanisms to detect internal defects in real-time Gas Metal Arc Welding with an F1 Score of 0.99. By integrating explainable AI, the study enhances trust in industrial inspection systems by identifying critical features within image and sound spectrograms for specific defect types like porosity and lack of penetration. The work advances practical applications of machine learning in manufacturing automation through robust multi-modal data fusion.
Explainable Temporal Attention-based Defect Detection For Fillet Joints in Real-Time Gas Metal Arc Welding Based on Multi-modal Data
arXiv:2609.07893v1 Announce Type: cross 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.
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.
Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2609.07893 [cs.AI]
(or arXiv:2609.07893v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.07893 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 234 words