Assisted Data Analysis for Nondestructive Evaluation
e-Journal of Nondestructive Testing · 2026-07 · 31 (7)
DOI: 10.58286/33231 ↗At a glance
Journal article in e-Journal of Nondestructive Testing, 2026-07. Written by Eric A. Lindgren.
Abstract (original language)
There is increased exploration in using artificial intelligence and machine learning (AI/ML) for nondestructive evaluation (NDE) data analysis. However, data required for robust training of algorithms are limited and use of simulated data is challenged by the variability and complexity found in engineered systems. To facilitate model selection as a function of available data, this work explores the impact of data quantity and quality on the accuracy of common AI/ML algorithms. In addition, it covers methods being exploited for aviation applications that integrate heuristics and model-based techniques to assist in the analysis of NDE data. While assisting in analysis of NDE data, an additional benefit is relieving human inspectors of the tedious workload that can compromised performance. Several case studies for both metallic and polymer matrix composite structures are addressed. These include Assisted Data Analysis (ADA) algorithms that combined at least two of the three classes of algorithms to realize inspection objectives where the capability is validated by sensitivity or probability of detection studies. This approach has enabled assessments of complex and/or highly variable aerospace structures.
Cite
APA
Lindgren, E. A. (2026). Assisted Data Analysis for Nondestructive Evaluation. e-Journal of Nondestructive Testing, 31(7). https://doi.org/10.58286/33231
Vancouver
Lindgren EA. Assisted Data Analysis for Nondestructive Evaluation. e-Journal of Nondestructive Testing. 2026;31(7). doi:10.58286/33231
BibTeX
@article{Lindgren2026,
author = {Lindgren, Eric A.},
title = {Assisted Data Analysis for Nondestructive Evaluation},
journal = {e-Journal of Nondestructive Testing},
year = {2026},
volume = {31},
number = {7},
doi = {10.58286/33231}
}
EUVIMED