AI-Assisted In-Vessel Visual Inspections
e-Journal of Nondestructive Testing · 2026-07 · 31 (7)
DOI: 10.58286/33359 ↗Kurz gefasst
Fachartikel in der Zeitschrift e-Journal of Nondestructive Testing, 2026-07. Verfasst von Thiago Osorio.
Abstract (Originalsprache)
Nuclear power plants periodically perform visual examinations of reactor internals. These inspections are often on the outage critical path and subject examiners to unfavorable human factors as they are required to maintain a high level of focus for prolonged times while performing monotonous activities in challenging environments. While these conditions challenge inspection reliability, there are numerous opportunities to leverage machine vision technology in support of these examination activities that can help alleviate many of these issues and potentially lead to increased reliability. This talk presents an AI solution being developed to assist examiners in remote in-vessel visual examinations of reactor internals, both in real-time and in post-inspection review. Field trials at five different nuclear power plants have been completed to date in the US and Europe and the technology is considered ready for further deployment. The presentation will discuss field performance, observations and lessons learned, as well as gaps and further opportunities.
Zitieren
APA
Osorio, T. (2026). AI-Assisted In-Vessel Visual Inspections. e-Journal of Nondestructive Testing, 31(7). https://doi.org/10.58286/33359
Vancouver
Osorio T. AI-Assisted In-Vessel Visual Inspections. e-Journal of Nondestructive Testing. 2026;31(7). doi:10.58286/33359
BibTeX
@article{Osorio2026,
author = {Osorio, Thiago},
title = {AI-Assisted In-Vessel Visual Inspections},
journal = {e-Journal of Nondestructive Testing},
year = {2026},
volume = {31},
number = {7},
doi = {10.58286/33359}
}
EUVIMED