EUVIMEDEUVIMED entdecken
Crossref

Enhanced Aircraft Visual Inspection: Improving Defect Detection with Deflectometry, AI Assistance, and Synthetic Data Augmentation

Raphaël Viards, Henri Marticou, Jérémy Pirard

e-Journal of Nondestructive Testing · 2026-07 · 31 (7)

DOI: 10.58286/33550 ↗

Kurz gefasst

Fachartikel in der Zeitschrift e-Journal of Nondestructive Testing, 2026-07. Verfasst von Raphaël Viards und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aircraft maintenance relies heavily on visual inspections, a process that is labor-intensive, time-consuming and prone to human factor effects. To improve efficiency and accuracy, we introduce an AI-assisted inspection process, leveraging a patented LED bar deflectometry system that enhances dents detection, along with high-resolution imaging for the detection of other types of defects such as lightning strikes, corrosion, cracks or scratches. To address the scarcity of real-world defect data, we develop a hybrid synthetic data augmentation pipeline which extracts features from real images, adapts them to the Operational Design Domain (ODD), and blends them onto flawless aircraft surfaces. This approach enables the effective training of deep learning models for multi-defects detection. We perform a comparative evaluation against traditional human inspection, demonstrating the strong performance of our AI-assisted inspection approach. Additionally, full-scale validation using a drone as an autonomous vector system confirms the scalability of our process.

Zitieren

APA

Viards, R., Marticou, H., & Pirard, J. (2026). Enhanced Aircraft Visual Inspection: Improving Defect Detection with Deflectometry, AI Assistance, and Synthetic Data Augmentation. e-Journal of Nondestructive Testing, 31(7). https://doi.org/10.58286/33550

Vancouver

Viards R, Marticou H, Pirard J. Enhanced Aircraft Visual Inspection: Improving Defect Detection with Deflectometry, AI Assistance, and Synthetic Data Augmentation. e-Journal of Nondestructive Testing. 2026;31(7). doi:10.58286/33550

BibTeX
@article{Viards2026,
  author = {Viards, Raphaël and Marticou, Henri and Pirard, Jérémy},
  title = {Enhanced Aircraft Visual Inspection: Improving Defect Detection with Deflectometry, AI Assistance, and Synthetic Data Augmentation},
  journal = {e-Journal of Nondestructive Testing},
  year = {2026},
  volume = {31},
  number = {7},
  doi = {10.58286/33550}
}
Kostenlos starten →