Deep-learning-based system-scale diagnosis of a nuclear power plant with multiple infrared cameras
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
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
Abstract
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
참고문헌 (30)
- K. Moshkbar-Bakhsayesh, "Transient identification in nuclear power plants : a review", Prog. Nucl. Energy, 67, pp.23~32 (2013)
- M. M. Najafabadi, "Deep learning applications and challenges in big data analytics", Journal of Big Data, 2, pp.1~ (2015)
- H. M. Park, "Wall temperature prediction at critical heat flux using a machine learning model", Ann. Nucl. Energy, 141, pp.107334~ (2020)
- T. V. Santosh, "Application of artificial neural networks to nuclear power plant transient diagnosis", Reliab. Eng. Syst. Saf, 92, pp.1468~1472 (2007)
- H. A. Saeed, "Novel fault diagnosis scheme utilizing deep learning networks", Prog. Nucl. Energy, 118, pp.103066~ (2020)
- G. Lee, "A convolutional neural network model for abnormality diagnosis in a nuclear power plant", Appl. Soft Comput, 99, pp.106874~ (2020)
- S. Bagavathiappan, "Infrared thermography for condition monitoring e a review", Infrared Phys. Technol, 60, pp.35~55 (2013)
- S. Albawi, "Understanding of a convolutional neural network", 2017 International Conference On Engineering And Technology (ICET) (2017)
- O. Janssens, "Deep learning for infrared thermal image based machine health monitoring", IEEE, 2018, pp.99, 151~159
- J. S. Kim, "Infrared thermal image-based sustainable fault detection for electrical facilities", Sustainability, 13, pp.557~ (2021)
- A. Nasiri, "Intelligent fault diagnosis of cooling radiator based on deep learning analysis of infrared thermal images", Appl. Therm. Eng, 163, pp.114410~ (2019)
- J. Yang, "Infrared thermal imaging-based crack detection using deep learning", IEEE Access, 7, pp.182060~182077 (2019)
- 김경모, "Design and operation of the transparent integral effect test facility, URI-LO for nuclear innovation platform", Nuclear Engineering and Technology, 53(3), pp.776~792 (2021), 한국원자력학회[DOI]
- M. Ishii, "Scaling laws for thermal-hydraulic system under single phase and two-phase natural circulation", Nucl. Eng. Des, 81, pp.411~425 (1984)
- K. M. Kim, "Integral Effect Test in Visualization Basis 3D Printed Test Facility for Improved Application of Innovative Technology", International Topical Meeting on Nuclear Reactor Thermal Hydraulics, NURETH-18 (2019)
- X. G. Yu, "Systematic analysis of a station blackout scenario for APR1400 with test facility ATLAS and MARS code from scaling viewpoint", Nucl. Eng. Des, 259, pp.205~220 (2013)
- K. H. Lee, "An integral loop test and MARS code analysis for a DVI line break LOCA in the APR1400", Nucl. Eng. Des, 238, pp.3336~3347 (2008)
- S. Kim, "Analysis of an ATLAS 6-in. cold-leg break simulation with MARS code", Ann. Nucl. Energy, 63, pp.268~275 (2014)
- 박수용, "COMPARATIVE ANALYSIS OF STATION BLACKOUT ACCIDENT PROGRESSION IN TYPICAL PWR, BWR, AND PHWR", Nuclear Engineering and Technology, 44(3), pp.311~322 (2012), 한국원자력학회
- A. Prosek, "Long-term station blackout accident analysis of a PWR with RELAP5", MOD3.3, 2013, pp.2013, 851987~
- A. Canziani, "An Analysis of Deep Neural Network Models for Practical Application", 07678 arXiv preprint arXic:1605, ~ (2016)
- A. Krizhevsky, "Imagenet classification with deep convolutional neural networks?", Communications of the ACM, 60(6), pp.84~90 (2012)
- C. Szegedy, "Going deeper with convolutions", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2015)
- K. Simonyan, "Very Deep Convolutional Networks for Large-Scale Image Recognition", arXiv:1409.1556, ~ (2014)
- K. He, "Deep residual learning for image recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
- G. Huang, "Densely connected convolutional networks", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2017)
- S. Ruder, "An Overview of Gradient Descent Optimization Algorithms", arXiv preprint arXiv:1609.04747, ~ (2016)
- C. Sammut, "Encyclopedia of Machine Learning" (2011), Springer
- M. Vakili, "Performance Analysis and Comparison of Machine and Deep Learning Algorithms for IoT Data Classification", arXiv preprint arXiv:2001.09636, ~ (2020)
- R.R. Selvaraju, "Grad-cam:visual explanations from deep networks via gradient-based localization", Proceedings of the IEEE International Conference on Computer Vision, pp.618~626 (2017)