Generative AI in NDE: Connecting human expertise and data for enhanced inspection support
e-Journal of Nondestructive Testing · 2026-07 · 31 (7)
DOI: 10.58286/33041 ↗Kurz gefasst
Fachartikel in der Zeitschrift e-Journal of Nondestructive Testing, 2026-07. Verfasst von Marco Induti und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Artificial intelligence is not a new concept, but the arrival of generative AI has changed how people perceive and interact with it, bringing advanced capabilities into everyday work. The speed of adoption highlights its impact, especially in knowledge-based and regulated domains. Swiss Safety Center and SVTI operate in the TIC sector (Testing, Inspection and Certification), where inspection quality relies on experienced professionals. Across professional networks, including the NDT community, discussions increasingly focus on an ageing workforce, a shortage of qualified inspectors and the difficulty of transferring tacit knowledge. As inspections grow more complex, tools that support expert judgement become essential. To address this, we are developing the IVA-Inspector Virtual Assistant, a generative-AI tool that assists inspectors during preparation, execution and reporting. IVA retrieves contextual information from reports, standards, drawings and certificates. Because foundation models do not store enterprise data, IVA uses a Retrieval Augmented Generation (RAG) architecture to ensure answers remain grounded in trusted documents. Applied first within the Kesselinspektorat (Pressure Vessel Inspectorate), IVA aims to reduce administrative workload, strengthen knowledge continuity and support more consistent inspection decisions by providing structured access to standards, inspection history and domain knowledge.
Zitieren
APA
Induti, M., Romito, C., Cipolla, S., Trzebiatowski, O. V., & Goyal, P. (2026). Generative AI in NDE: Connecting human expertise and data for enhanced inspection support. e-Journal of Nondestructive Testing, 31(7). https://doi.org/10.58286/33041
Vancouver
Induti M, Romito C, Cipolla S, Trzebiatowski OV, Goyal P. Generative AI in NDE: Connecting human expertise and data for enhanced inspection support. e-Journal of Nondestructive Testing. 2026;31(7). doi:10.58286/33041
BibTeX
@article{Induti2026,
author = {Induti, Marco and Romito, Carlo and Cipolla, Stefano and Trzebiatowski, Oliver von and Goyal, Piyushi},
title = {Generative AI in NDE: Connecting human expertise and data for enhanced inspection support},
journal = {e-Journal of Nondestructive Testing},
year = {2026},
volume = {31},
number = {7},
doi = {10.58286/33041}
}
EUVIMED