| Issue |
MATEC Web Conf.
Volume 413, 2025
International Conference on Measurement, AI, Quality and Sustainability (MAIQS 2025)
|
|
|---|---|---|
| Article Number | 05004 | |
| Number of page(s) | 5 | |
| Section | Artificial Intelligence for NDT | |
| DOI | https://doi.org/10.1051/matecconf/202541305004 | |
| Published online | 01 October 2025 | |
LSTM based SCC detection using ultrasonic testing based data
1 Department of Mechanical and Aerospace Engineering, Brunel University of London, Uxbridge UB8 3PH, UK
2 TWI Ltd, Granta Park, Great Abington, Cambridge CB21 6AL, UK
* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.
Abstract
Recent trends in the field of structural integrity highlight the integration of Artificial Intelligence (AI) with related domains such as Structural Health Monitoring (SHM), Non-Destructive Evaluation (NDE), and the assessment of Stress Corrosion Cracking (SCC). AI plays a pivotal role in developing intelligent solutions to complex challenges, particularly in the detection and characterization of SCC. While several techniques are available, this paper focuses on the Ultrasonic Testing (UT) based Non-Destructive Testing (NDT) method integrated with Artificial Intelligence (AI), making it a robust Industry 4.0 solution. Deep learning, a subset of Artificial Intelligence and Machine Learning, is already considered as a key technology in Industry 4.0 solutions. This paper discusses the detection of SCC in steel using UT based data and deep learning. The trained neural network model will be used for the detection of SCC in the steel.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.