Semantic Segmentation of Micrographs for Nuclear Fuel Analysis and Degradation Quantification
When fuel materials for high-temperature gas-cooled nuclear reactors are quantification tested, significant analysis is required to establish their stability under various proposed accident scenarios, as well as to assess degradation over time. Typically, samples are examined by lab assistants train...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10287929/ |
_version_ | 1797643647931383808 |
---|---|
author | Christopher Snyder Katherine I. Montoya David Patrick Jordan Stone Daniel Mohanadhas Elizabeth S. Sooby Amanda S. Fernandez |
author_facet | Christopher Snyder Katherine I. Montoya David Patrick Jordan Stone Daniel Mohanadhas Elizabeth S. Sooby Amanda S. Fernandez |
author_sort | Christopher Snyder |
collection | DOAJ |
description | When fuel materials for high-temperature gas-cooled nuclear reactors are quantification tested, significant analysis is required to establish their stability under various proposed accident scenarios, as well as to assess degradation over time. Typically, samples are examined by lab assistants trained to capture micrograph images used to analyze the degradation of a material. Analysis of these micrographs still require manual intervention which is time-consuming and can introduce human-error. While machine learning and computer vision models would be useful to this analysis, data for training such models is limited due to physical experiment costs, including lab hours and materials. This collaborative research are: 1) establishes an open dataset of micrographs and semantic labels named Graphite-23; 2) analyzes semantic segmentation architectures against the new data; and 3) contributes open source code for the community to progress research in degradation analysis of materials. A U-Net architecture with various backbones demonstrates competitive performance on the proposed dataset, with an mIoU up to 0.83, establishing a clear baseline for future research in this intersection of fields. |
first_indexed | 2024-03-11T14:17:56Z |
format | Article |
id | doaj.art-1a133c70747541ab9ded215f5365e551 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-11T14:17:56Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-1a133c70747541ab9ded215f5365e5512023-10-31T23:00:33ZengIEEEIEEE Access2169-35362023-01-011111851211852010.1109/ACCESS.2023.332607410287929Semantic Segmentation of Micrographs for Nuclear Fuel Analysis and Degradation QuantificationChristopher Snyder0Katherine I. Montoya1https://orcid.org/0000-0003-2695-5086David Patrick2https://orcid.org/0000-0003-2556-8818Jordan Stone3Daniel Mohanadhas4https://orcid.org/0009-0004-5356-8561Elizabeth S. Sooby5https://orcid.org/0000-0001-5376-3413Amanda S. Fernandez6https://orcid.org/0000-0003-2397-0838Department of Computer Science, The University of Texas at San Antonio (UTSA), San Antonio, TX, USADepartment of Physics and Astronomy, The University of Texas at San Antonio (UTSA), San Antonio, TX, USADepartment of Computer Science, The University of Texas at San Antonio (UTSA), San Antonio, TX, USADepartment of Physics and Astronomy, The University of Texas at San Antonio (UTSA), San Antonio, TX, USADepartment of Computer Science, The University of Texas at San Antonio (UTSA), San Antonio, TX, USADepartment of Physics and Astronomy, The University of Texas at San Antonio (UTSA), San Antonio, TX, USADepartment of Computer Science, The University of Texas at San Antonio (UTSA), San Antonio, TX, USAWhen fuel materials for high-temperature gas-cooled nuclear reactors are quantification tested, significant analysis is required to establish their stability under various proposed accident scenarios, as well as to assess degradation over time. Typically, samples are examined by lab assistants trained to capture micrograph images used to analyze the degradation of a material. Analysis of these micrographs still require manual intervention which is time-consuming and can introduce human-error. While machine learning and computer vision models would be useful to this analysis, data for training such models is limited due to physical experiment costs, including lab hours and materials. This collaborative research are: 1) establishes an open dataset of micrographs and semantic labels named Graphite-23; 2) analyzes semantic segmentation architectures against the new data; and 3) contributes open source code for the community to progress research in degradation analysis of materials. A U-Net architecture with various backbones demonstrates competitive performance on the proposed dataset, with an mIoU up to 0.83, establishing a clear baseline for future research in this intersection of fields.https://ieeexplore.ieee.org/document/10287929/Computer visiondeep learningfuel analysisgraphiteneural networksnuclear materials |
spellingShingle | Christopher Snyder Katherine I. Montoya David Patrick Jordan Stone Daniel Mohanadhas Elizabeth S. Sooby Amanda S. Fernandez Semantic Segmentation of Micrographs for Nuclear Fuel Analysis and Degradation Quantification IEEE Access Computer vision deep learning fuel analysis graphite neural networks nuclear materials |
title | Semantic Segmentation of Micrographs for Nuclear Fuel Analysis and Degradation Quantification |
title_full | Semantic Segmentation of Micrographs for Nuclear Fuel Analysis and Degradation Quantification |
title_fullStr | Semantic Segmentation of Micrographs for Nuclear Fuel Analysis and Degradation Quantification |
title_full_unstemmed | Semantic Segmentation of Micrographs for Nuclear Fuel Analysis and Degradation Quantification |
title_short | Semantic Segmentation of Micrographs for Nuclear Fuel Analysis and Degradation Quantification |
title_sort | semantic segmentation of micrographs for nuclear fuel analysis and degradation quantification |
topic | Computer vision deep learning fuel analysis graphite neural networks nuclear materials |
url | https://ieeexplore.ieee.org/document/10287929/ |
work_keys_str_mv | AT christophersnyder semanticsegmentationofmicrographsfornuclearfuelanalysisanddegradationquantification AT katherineimontoya semanticsegmentationofmicrographsfornuclearfuelanalysisanddegradationquantification AT davidpatrick semanticsegmentationofmicrographsfornuclearfuelanalysisanddegradationquantification AT jordanstone semanticsegmentationofmicrographsfornuclearfuelanalysisanddegradationquantification AT danielmohanadhas semanticsegmentationofmicrographsfornuclearfuelanalysisanddegradationquantification AT elizabethssooby semanticsegmentationofmicrographsfornuclearfuelanalysisanddegradationquantification AT amandasfernandez semanticsegmentationofmicrographsfornuclearfuelanalysisanddegradationquantification |