Deep-learning-based system-scale diagnosis of a nuclear power plant with multiple infrared cameras
Comprehensive condition monitoring of large industry systems such as nuclear power plants (NPPs) is essential for safety and maintenance. In this study, we developed novel system-scale diagnostic technology based on deep-learning and IR thermography that can efficiently and cost-effectively classify...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-02-01
|
Series: | Nuclear Engineering and Technology |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1738573322004934 |
_version_ | 1797897307929182208 |
---|---|
author | Ik Jae Jin Do Yeong Lim In Cheol Bang |
author_facet | Ik Jae Jin Do Yeong Lim In Cheol Bang |
author_sort | Ik Jae Jin |
collection | DOAJ |
description | Comprehensive condition monitoring of large industry systems such as nuclear power plants (NPPs) is essential for safety and maintenance. In this study, we developed novel system-scale diagnostic technology based on deep-learning and IR thermography that can efficiently and cost-effectively classify system conditions using compact Raspberry Pi and IR sensors. This diagnostic technology can identify the presence of an abnormality or accident in whole system, and when an accident occurs, the type of accident and the location of the abnormality can be identified in real-time. For technology development, the experiment for the thermal image measurement and performance validation of major components at each accident condition of NPPs was conducted using a thermal-hydraulic integral effect test facility with compact infrared sensor modules. These thermal images were used for training of deep-learning model, convolutional neural networks (CNN), which is effective for image processing. As a result, a proposed novel diagnostic was developed that can perform diagnosis of components, whole system and accident classification using thermal images. The optimal model was derived based on the modern CNN model and performed prompt and accurate condition monitoring of component and whole system diagnosis, and accident classification. This diagnostic technology is expected to be applied to comprehensive condition monitoring of nuclear power plants for safety. |
first_indexed | 2024-04-10T07:56:29Z |
format | Article |
id | doaj.art-8018dcc7cba44731994f1315aecd10f2 |
institution | Directory Open Access Journal |
issn | 1738-5733 |
language | English |
last_indexed | 2024-04-10T07:56:29Z |
publishDate | 2023-02-01 |
publisher | Elsevier |
record_format | Article |
series | Nuclear Engineering and Technology |
spelling | doaj.art-8018dcc7cba44731994f1315aecd10f22023-02-23T04:30:43ZengElsevierNuclear Engineering and Technology1738-57332023-02-01552493505Deep-learning-based system-scale diagnosis of a nuclear power plant with multiple infrared camerasIk Jae Jin0Do Yeong Lim1In Cheol Bang2Department of Nuclear Engineering Ulsan National Institute of Science and Technology (UNIST), 50 UNIST-gil, Ulju-gun, Ulsan, 44919, Republic of KoreaDepartment of Nuclear Engineering Ulsan National Institute of Science and Technology (UNIST), 50 UNIST-gil, Ulju-gun, Ulsan, 44919, Republic of KoreaCorresponding author.; Department of Nuclear Engineering Ulsan National Institute of Science and Technology (UNIST), 50 UNIST-gil, Ulju-gun, Ulsan, 44919, Republic of KoreaComprehensive condition monitoring of large industry systems such as nuclear power plants (NPPs) is essential for safety and maintenance. In this study, we developed novel system-scale diagnostic technology based on deep-learning and IR thermography that can efficiently and cost-effectively classify system conditions using compact Raspberry Pi and IR sensors. This diagnostic technology can identify the presence of an abnormality or accident in whole system, and when an accident occurs, the type of accident and the location of the abnormality can be identified in real-time. For technology development, the experiment for the thermal image measurement and performance validation of major components at each accident condition of NPPs was conducted using a thermal-hydraulic integral effect test facility with compact infrared sensor modules. These thermal images were used for training of deep-learning model, convolutional neural networks (CNN), which is effective for image processing. As a result, a proposed novel diagnostic was developed that can perform diagnosis of components, whole system and accident classification using thermal images. The optimal model was derived based on the modern CNN model and performed prompt and accurate condition monitoring of component and whole system diagnosis, and accident classification. This diagnostic technology is expected to be applied to comprehensive condition monitoring of nuclear power plants for safety.http://www.sciencedirect.com/science/article/pii/S1738573322004934System scale diagnosisNuclear power plantInfrared sensorDeep learningConvolutional neural networkFault detection |
spellingShingle | Ik Jae Jin Do Yeong Lim In Cheol Bang Deep-learning-based system-scale diagnosis of a nuclear power plant with multiple infrared cameras Nuclear Engineering and Technology System scale diagnosis Nuclear power plant Infrared sensor Deep learning Convolutional neural network Fault detection |
title | Deep-learning-based system-scale diagnosis of a nuclear power plant with multiple infrared cameras |
title_full | Deep-learning-based system-scale diagnosis of a nuclear power plant with multiple infrared cameras |
title_fullStr | Deep-learning-based system-scale diagnosis of a nuclear power plant with multiple infrared cameras |
title_full_unstemmed | Deep-learning-based system-scale diagnosis of a nuclear power plant with multiple infrared cameras |
title_short | Deep-learning-based system-scale diagnosis of a nuclear power plant with multiple infrared cameras |
title_sort | deep learning based system scale diagnosis of a nuclear power plant with multiple infrared cameras |
topic | System scale diagnosis Nuclear power plant Infrared sensor Deep learning Convolutional neural network Fault detection |
url | http://www.sciencedirect.com/science/article/pii/S1738573322004934 |
work_keys_str_mv | AT ikjaejin deeplearningbasedsystemscalediagnosisofanuclearpowerplantwithmultipleinfraredcameras AT doyeonglim deeplearningbasedsystemscalediagnosisofanuclearpowerplantwithmultipleinfraredcameras AT incheolbang deeplearningbasedsystemscalediagnosisofanuclearpowerplantwithmultipleinfraredcameras |