ORIGINAL RESEARCH article
Front. Mater.
Sec. Structural Materials
Volume 12 - 2025 | doi: 10.3389/fmats.2025.1659494
This article is part of the Research TopicJoining and Welding of New and Dissimilar Materials - Volume IIIView all 5 articles
Microstructural Influence on Learning-Based Defect Detection in Dissimilar Metal Welds
Provisionally accepted
- Chang’an University, Xi'an, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Accurate defect detection in dissimilar metal welds (DMWs) remains a major challenge due to heterogeneous microstructures and imaging noise. In this study, we propose a novel deep learning framework, DynaWave-Net, combined with a Guided Progressive Distillation (GPD) strategy, to address these challenges by integrating microstructural priors and frequency-domain features. The proposed model incorporates dynamic geometry-aware encoding and wavelet-based attention to capture both structural deformations and high-frequency defect signatures. Extensive experiments on multiple real-world datasets demonstrate that our approach significantly outperforms existing methods, achieving up to 18% improvement in precision and enhanced robustness to structural noise. Furthermore, the lightweight architecture enables real-time deployment on edge devices, highlighting the practical relevance of this work for industrial inspection in energy, aerospace, and manufacturing sectors.
Keywords: Weld defect detection, Dissimilar metal welds, deep learning, Wavelet attention, Domain adaptation
Received: 04 Jul 2025; Accepted: 21 Aug 2025.
Copyright: © 2025 Gao. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Zhixin Gao, Chang’an University, Xi'an, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.