Reconstruction-Driven Induction Thermography for AI-Assisted Surface Defect Detection in Welded Structures

Реконструкционно-ориентированная индукционная термография для обнаружения поверхностных дефектов в сварных конструкциях с использованием искусственного интеллекта
Xiang Zhang, Shenghao Huang, Xiaolu Cui, Yu Cao, Dong Wang, Guiyun Tian
2026-07-12

DeepLabv3+ segmentationinduction thermographyspeed-based reconstructionsurface defect detectionwelded steel structures
Welding is widely used to join steel components in energy storage systems, wind power generation systems, and transportation infrastructure. During service, surface defects in steel welds can promote rapid crack propagation and sudden fracture. To address this issue, this study presents an induction thermography framework for post-weld quality inspection of surface-breaking defects in welded steel structures. First, a yoke excitation structure was optimized and evaluated through numerical simulation and experimental validation, and its performance was compared with those of a straight coil and a three-loop coil. The results show that the yoke configuration maintains sufficient heating intensity in the weld region while improving the spatial uniformity of the thermal response. Furthermore, a speed-based reconstruction method was developed to reduce the effects of specimen motion and coil occlusion. By aligning thermal responses from the same physical locations in sequential thermograms, the method reconstructs a continuous temperature field over an extended inspection area. Consequently, the reconstructed images retain clear crack-related thermal features and provide stable inputs for automated analysis. In addition, DeepLabv3+, DSCA-UNet, and feature pyramid network (FPN) were used as representative segmentation models to evaluate the suitability of the reconstructed thermograms for automated defect extraction. On the current laboratory dataset, the three models achieved precision values of 90.4%, 88.6%, and 92.6%, respectively. These results indicate the potential of the proposed framework, while further validation with larger datasets and natural weld defects is still required.
1
A speed-based reconstruction method compensated for specimen motion and coil occlusion by aligning sequential thermograms and reconstructing continuous temperature fields.
2
An induction thermography framework was developed for post-weld inspection of surface-breaking defects in steel structures.
3
DeepLabv3+, DSCA-UNet, and FPN achieved precision values of 90.4%, 88.6%, and 92.6%, respectively, on the laboratory dataset; larger-scale validation remains necessary.
4
Reconstructed thermograms preserved clear crack-related thermal features and provided stable inputs for automated defect segmentation.
5
The optimized yoke excitation maintained sufficient weld-region heating while improving thermal-response spatial uniformity compared with straight and three-loop coils.

surface-breaking defects in welded steel structures

induction-thermography detection and reconstruction-based segmentation performance for crack-related thermal features

Publication Details
Publication Date
2026-07-12
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Xiang Zhang
Shenghao Huang
Xiaolu Cui
Yu Cao
Dong Wang
Guiyun Tian
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%