Automated Borescope Inspection with AI Support for Visual Testing
e-Journal of Nondestructive Testing · 2026-07 · 31 (7)
DOI: 10.58286/33087 ↗Kurz gefasst
Fachartikel in der Zeitschrift e-Journal of Nondestructive Testing, 2026-07. Verfasst von Marco Induti und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Borescope inspection is widely used for internal visual testing of components where direct access is not possible. Despite advances in imaging technology, the inspection process remains largely manual and strongly operator-dependent. Probe manipulation, viewing angle selection and real-time interpretation rely heavily on the inspector’s experience, which may lead to variability in defect assessment and incomplete inspection coverage. This work presents an automated borescope inspection system developed for the internal inspection of small-diameter tubes. The system drives a flexible borescope along the tube axis using encoder-controlled motion, enabling repeatable image acquisition and precise position mapping for each frame. The acquired images are analyzed using an anomaly-detection model trained on representative inspection data. By combining controlled acquisition with AI-assisted analysis, the system provides traceable inspection results and structured documentation while preserving the inspector’s role in the final evaluation. Experimental validation indicates that the automated approach improves repeatability and significantly reduces inspection time compared to conventional manual procedures.
Zitieren
APA
Induti, M., Tinari, M., Yersin, M., Stara, E., & Scaccabarozzi, L. (2026). Automated Borescope Inspection with AI Support for Visual Testing. e-Journal of Nondestructive Testing, 31(7). https://doi.org/10.58286/33087
Vancouver
Induti M, Tinari M, Yersin M, Stara E, Scaccabarozzi L. Automated Borescope Inspection with AI Support for Visual Testing. e-Journal of Nondestructive Testing. 2026;31(7). doi:10.58286/33087
BibTeX
@article{Induti2026,
author = {Induti, Marco and Tinari, Massimiliano and Yersin, Manuel and Stara, Erik and Scaccabarozzi, Luca},
title = {Automated Borescope Inspection with AI Support for Visual Testing},
journal = {e-Journal of Nondestructive Testing},
year = {2026},
volume = {31},
number = {7},
doi = {10.58286/33087}
}
EUVIMED