Advances and Applications of Deep Learning in NDT of Welding

DOI

10.2991/978-94-6463-821-9_88How to use a DOI?

Keywords

Weld Defects; Deep Learning; Nondestructive Testing

Abstract

With the advancement of the industrial intelligence process, as the core link to ensure the structural safety of major projects, the demand for precision and efficiency of weld quality inspection is increasing. Recently, the breakthrough progress of deep learning technology has promoted the strategic transformation of weld quality assessment from traditional manual interpretation to the direction of intelligence and automation. This paper systematically sorts out the status of the integration and application of deep learning technology with mainstream weld non-destructive testing (NDT) methods. First, this paper classifies weld defects. Secondly, this paper constructs a technology matrix of NDT welding methods, explaining the advantages, disadvantages, and application occasions of various methods. Finally, using a literature review and case study approach, the paper summarises the practical applications of deep learning in these methods, providing insights into current application practices and suggestions for future developments. By systematically combining interdisciplinary research results, this study integrates the key technology mapping in the field of deep learning and weld NDT, which has an important guiding value for grasping the research hotspots and breaking through technical bottlenecks in the field.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yuanfan Xia
PY  - 2025
DA  - 2025/08/31
TI  - Advances and Applications of Deep Learning in NDT of Welding
BT  - Proceedings of the 2025 2nd International Conference on Mechanics, Electronics Engineering and Automation (ICMEEA 2025)
PB  - Atlantis Press
SP  - 919
EP  - 930
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-821-9_88
DO  - 10.2991/978-94-6463-821-9_88
ID  - Xia2025
ER  -