Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 15, 2026SensorsOpen Access

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

View Full Paper
Ask AI
Bookmark
Share

Authors

XZXiang ZhangSHShenghao HuangXCXiaolu Cui

Discussion

Loading...

Member takes

Overview

Randomized trial evaluates surface defect detection in welded structures, indicating promising automated analysis methods.

Key Points

  • This research aims to develop an effective framework for detecting surface defects in welded steel structures using induction thermography.
  • Optimized yoke excitation structure evaluated through numerical simulation and experimental validation.
  • Developed a speed-based reconstruction method to align thermal responses from sequential thermograms.
  • Applied DeepLabv3+, DSCA-UNet, and feature pyramid network for defect segmentation evaluation.
  • Precision values for segmentation models were 90.4%, 88.6%, and 92.6%, respectively.
  • Reconstruction method effectively reduced motion effects and improved thermal response uniformity.
  • Yoke configuration maintained heating intensity in weld regions, enhancing inspection outcomes.

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/6a5722f088b21df87547fd79https://doi.org/10.3390/s26144422
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Leveraging thermal images for automatic surface defect detection in TIG welding process of thin metal sheets2026 · 2 citations
  2. 2Automatic image analysis of surface defects in hybrid welding of dissimilar joints for lifecycle enhancement2026 · 1 citations
  3. 3Induction thermography as a powerful tool to crack detectability and quantification: a feasibility study at consistent scanning speeds2025 · 1 citations
  4. 4Advanced active thermography for weld joint inspection2025
  5. 5Advancing Defect Detection in Laser Welding: A Machine Learning Approach Based on Spatter Feature Analysis2026 · 1 citations