AI for manual ultrasonic inspection
e-Journal of Nondestructive Testing · 2026-07 · 31 (7)
DOI: 10.58286/33570 ↗Kurz gefasst
Fachartikel in der Zeitschrift e-Journal of Nondestructive Testing, 2026-07. Verfasst von Oskari Jessen-Juhler und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Automated evaluation of phased array and TFM ultrasonic data has been successfully completed in recent years [1‑3]. However, the use of Artificial intelligence and Machine learning (AI/ML) has thus far been limited to encoded inspections, typically as post processing of data files from mechanized inspections. While mechanization is increasingly popular, manual inspections have unsurpassed flexibility and thus will remain important. It is of interest to use the recent machine learning techniques to also increase the performance and reliability of manual inspections. The present paper presents the development of AI/ML assitance for manual phased array inspection. Results on a prototype manual PA system with automated encoding and real-time AI/ML evaluation in one-shot and reconstructed scan-line modes are presented.
Zitieren
APA
Jessen-Juhler, O., Virkkunen, I., & Seuaciuc-osorio, T. (2026). AI for manual ultrasonic inspection. e-Journal of Nondestructive Testing, 31(7). https://doi.org/10.58286/33570
Vancouver
Jessen-Juhler O, Virkkunen I, Seuaciuc-osorio T. AI for manual ultrasonic inspection. e-Journal of Nondestructive Testing. 2026;31(7). doi:10.58286/33570
BibTeX
@article{JessenJuhler2026,
author = {Jessen-Juhler, Oskari and Virkkunen, Iikka and Seuaciuc-osorio, Thiago},
title = {AI for manual ultrasonic inspection},
journal = {e-Journal of Nondestructive Testing},
year = {2026},
volume = {31},
number = {7},
doi = {10.58286/33570}
}
EUVIMED