Back to Search Start Over

Using Deep Learning to Automate the Detection of Flaws in Nuclear Fuel Channel UT Scans.

Authors :
Hammad, Issam
Simpson, Ryan
Tsague, Hippolyte Djonon
Hall, Sarah
Source :
IEEE Transactions on Ultrasonics Ferroelectrics & Frequency Control; Jan2022, Vol. 69 Issue 1, p323-329, 7p
Publication Year :
2022

Abstract

Nuclear reactor inspections are critical to ensure the safety and reliability of a nuclear facility’s operation. In Canada, ultrasonic testing (UT) is used to inspect the health of pressure tubes that are part of Canada’s Deuterium Uranium (CANDU) reactor’s fuel channels. Currently, analysis of UT scans is performed by manual visualization and measurement to locate, characterize, and disposition flaws. Therefore, there is motivation to develop an automated method that is fast and accurate. In this article, a proof of concept (PoC) that automates the detection of flaws in nuclear fuel channel UT scans using a convolutional neural network (CNN) is presented. The CNN model was trained after constructing a dataset using historical UT scans and the corresponding inspection results. The requirement for this prototype was to identify the location of at least a portion of each flaw in UT scans while minimizing false positives (FPs). The proposed CNN model achieves this target by automatically identifying at least a portion of each flaw where further manual analysis is performed to identify the width, the length, and the type of the flaw. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
08853010
Volume :
69
Issue :
1
Database :
Complementary Index
Journal :
IEEE Transactions on Ultrasonics Ferroelectrics & Frequency Control
Publication Type :
Academic Journal
Accession number :
154764283
Full Text :
https://doi.org/10.1109/TUFFC.2021.3112078