Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Graph neural network based multiple accident diagnosis in nuclear power plants: Data optimization to represent the system configuration

  • Chae, Young Ho (Department of Nuclear and Quantum Engineering, Korea Advanced Institute of Science and Technology) ;
  • Lee, Chanyoung (Korea Atomic Energy Research Institute) ;
  • Han, Sang Min (Samsung Electronics) ;
  • Seong, Poong Hyun (Department of Nuclear and Quantum Engineering, Korea Advanced Institute of Science and Technology)
  • Received : 2021.07.30
  • Accepted : 2022.02.23
  • Published : 2022.08.25
Download PDF
⟨ Previous Next ⟩

Abstract

Because nuclear power plants (NPPs) are safety-critical infrastructure, it is essential to increase their safety and minimize risk. To reduce human error and support decision-making by operators, several artificial-intelligence-based diagnosis methods have been proposed. However, because of the nature of data-driven methods, conventional artificial intelligence requires large amount of measurement values to train and achieve enough diagnosis resolution. We propose a graph neural network (GNN) based accident diagnosis algorithm to achieve high diagnosis resolution with limited measurements. The proposed algorithm is trained with both the knowledge about physical correlation between components and measurement values. To validate the proposed methodology has a sufficiently high diagnostic resolution with limited measurement values, the diagnosis of multiple accidents was performed with limited measurement values and also, the performance was compared with convolution neural network (CNN). In case of the experiment that requires low diagnostic resolution, both CNN and GNN showed good results. However, for the tests that requires high diagnostic resolution, GNN greatly outperformed the CNN.

Keywords

Acknowledgement

This research was supported by the National R&D Program through the National Research Foundation of Korea (NRF) funded by the Korean Government. (MSIP: Ministry of Science, ICT and Future Planning) (No. NRF-2016R1A5A1013919).

References

  1. Man Cheol Kim, Poong Hyun Seong, An analytic model for situation assessment of nuclear power plant operators based on Bayesian inference, Reliab. Eng. Syst. Saf. 91 (2006) 270-282, 3. https://doi.org/10.1016/j.ress.2005.01.012
  2. Erik Hollnagel, Human reliability assessment in context, Nucl. Eng. Technol. 37 (2005) 159-166, 2.
  3. US Nuclear Regulatory Commission, Reactor Safety Study: an Assessment of Accident Risks in US Commercial Nuclear Power Plants, vol. 2, US Nuclear Regulatory Commission, 1975.
  4. https://opis.kins.re.kr/opis.
  5. Jin Kyun Park, et al., A Study on the Systematic Framework to Develop an Effective Diagnosis Procedure of the Nuclear Power Plants, Korea Atomic Energy Research Institute, 2003. No. KAERI/TR-2597/2003.
  6. Jae Whan Kim, et al., A Study on the Operator's Errors of Commission (EOC) in Accident Scenarios of Nuclear Power Plants: Methodology Development and Application, 2003.
  7. Khalil Moshkbar-Bakhshayesh, Mohammad B. Ghofrani, Transient identification in nuclear power plants: a review, Prog. Nucl. Energy 67 (2013) 23-32. https://doi.org/10.1016/j.pnucene.2013.03.017
  8. Gyumin Lee, Seung Jun Lee, Changyong Lee, A convolutional neural network model for abnormality diagnosis in a nuclear power plant, Appl. Soft Comput. 99 (2021) 106874. https://doi.org/10.1016/j.asoc.2020.106874
  9. Jaemin Yang, Daeil Lee, Jonghyun Kim, Accident diagnosis and autonomous control of safety functions during the startup operation of nuclear power plants using LSTM, in: International Conference on Applied Human Factors and Ergonomics, Springer, Cham, 2018.
  10. Kee-Choon Kwon, Jin-Hyung Kim, Accident identification in nuclear power plants using hidden Markov models, Eng. Appl. Artif. Intell. 12 (1999) 491-501, 4. https://doi.org/10.1016/S0952-1976(99)00011-1
  11. Victor Henrique Cabral Pinheiro, et al., Nuclear Power Plant accident identification system with "don't know" response capability: novel deep learning-based approaches, Ann. Nucl. Energy 137 (2020) 107111. https://doi.org/10.1016/j.anucene.2019.107111
  12. T.V. Santosh, et al., Diagnostic system for identification of accident scenarios in nuclear power plants using artificial neural networks, Reliab. Eng. Syst. Saf. 94 (2009) 759-762, 3. https://doi.org/10.1016/j.ress.2008.08.005
  13. Victor Henrique Cabral Pinheiro, Roberto Schirru, Genetic programming applied to the identification of accidents of a PWR nuclear power plant, Ann. Nucl. Energy 124 (2019) 335-341. https://doi.org/10.1016/j.anucene.2018.09.039
  14. Carla Regina Gomes, Jose Antonio Carlos Canedo Medeiros, Neural network of Gaussian radial basis functions applied to the problem of identification of nuclear accidents in a PWR nuclear power plant, Ann. Nucl. Energy 77 (2015) 285-293. https://doi.org/10.1016/j.anucene.2014.10.001
  15. Franco Scarselli, et al., The graph neural network model, IEEE Trans. Neural Network. 20 (2008) 61-80, 1. https://doi.org/10.1109/TNN.2008.2005605
  16. Jie Zhou, et al., Graph neural networks: a review of methods and applications, AI Open 1 (2020) 57-81. https://doi.org/10.1016/j.aiopen.2021.01.001
  17. David Raposo, et al., Discovering Objects and Their Relations from Entangled Scene Representations, 2017 arXiv preprint arXiv:1702.05068.
  18. Peter W. Battaglia, et al., Interaction Networks for Learning about Objects, Relations and Physics, 2016 arXiv preprint arXiv:1612.00222.
  19. David Duvenaud, et al., Convolutional Networks on Graphs for Learning Molecular Fingerprints, 2015 arXiv preprint arXiv:1509.09292.
  20. Steven Kearnes, et al., Molecular graph convolutions: moving beyond fingerprints, J. Comput. Aided Mol. Des. 30 (2016) 595-608, 8. https://doi.org/10.1007/s10822-016-9938-8
  21. Hao Peng, et al., Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networks, 2019, 04580 arXiv preprint arXiv:1906.
  22. Yongji Wu, et al., Graph convolutional networks with markov random field reasoning for social spammer detection, in: Proceedings of the AAAI Conference on Artificial Intelligence vol. 34, 2020, 1.
  23. Tian Bian, et al., Rumor detection on social media with bi-directional graph convolutional networks, in: Proceedings of the AAAI Conference on Artificial Intelligence 34, 2020, 1.
  24. Joan Bruna, et al., Spectral Networks and Locally Connected Networks on Graphs, 2013 arXiv preprint arXiv:1312.6203.
  25. Young Ho Chae, et al., A methodology for diagnosing FAC induced pipe thinning using accelerometers and deep learning models, Ann. Nucl. Energy 143 (2020) 107501. https://doi.org/10.1016/j.anucene.2020.107501
  26. Korea Atomic Energy Research Institute, Advanced Compact Nuclear Simulator Textbook, Nuclear Training Center in Korea Atomic Energy Research Institute.
  27. Diederik P. Kingma, Ba Jimmy, Adam: A Method for Stochastic Optimization, 2014 arXiv preprint arXiv:1412.6980.