DOI QR코드

DOI QR Code

An accident diagnosis algorithm using long short-term memory

  • Yang, Jaemin (Department of Nuclear Engineering, Chosun University) ;
  • Kim, Jonghyun (Department of Nuclear Engineering, Chosun University)
  • 투고 : 2018.02.03
  • 심사 : 2018.03.13
  • 발행 : 2018.05.25

초록

Accident diagnosis is one of the complex tasks for nuclear power plant (NPP) operators. In abnormal or emergency situations, the diagnostic activity of the NPP states is burdensome though necessary. Numerous computer-based methods and operator support systems have been suggested to address this problem. Among them, the recurrent neural network (RNN) has performed well at analyzing time series data. This study proposes an algorithm for accident diagnosis using long short-term memory (LSTM), which is a kind of RNN, which improves the limitation for time reflection. The algorithm consists of preprocessing, the LSTM network, and postprocessing. In the LSTM-based algorithm, preprocessed input variables are calculated to output the accident diagnosis results. The outputs are also postprocessed using softmax to determine the ranking of accident diagnosis results with probabilities. This algorithm was trained using a compact nuclear simulator for several accidents: a loss of coolant accident, a steam generator tube rupture, and a main steam line break. The trained algorithm was also tested to demonstrate the feasibility of diagnosing NPP accidents.

키워드

참고문헌

  1. O. Maruo, et al., HSI for Monitoring the Critical Safety Functions Status Tree of a NPP, International Nuclear Atlantic Conference, Recife, PE, Brazil, Nov. 24-29, 2013.
  2. J.K. Vaurio, Safety-related decision making at a nuclear power plant, Nucl. Eng. Des. 185 (1998) 335-345. https://doi.org/10.1016/S0029-5493(98)00225-8
  3. T. Kontogiannis, Stress and operator decision making in coping with emergencies, Int. J. Hum. Comput. Inter. 45 (1996) 75-104. https://doi.org/10.1006/ijhc.1996.0043
  4. David D. Woods, Coping with complexity: the psychology of human behaviour in complex systems, in: Tasks, Errors, and Mental Models, Taylor & Francis, Inc, 1988, pp. 128-148.
  5. David Meister, Cognitive behavior of nuclear reactor operators, Int. J. Ind. Ergonom. 16.2 (1995) 109-122. https://doi.org/10.1016/0169-8141(94)00089-L
  6. Nuclear Energy Agency, Critical Operator Actions: Human Reliability Modeling and Data Issues, 1998. NEA/CSNI/R(98)1.
  7. T.V. Santosh, et al., Application of artificial neural networks to nuclear power plant transient diagnosis, Reliab. Eng. Syst. Saf. 92 (10) (2007) 1468-1472. https://doi.org/10.1016/j.ress.2006.10.009
  8. Jinkyun Park, Wondea Jung, A study on the systematic framework to develop effective diagnosis procedures of nuclear power plants, Reliab. Eng. Syst. Saf. 84.3 (2004) 319-335. https://doi.org/10.1016/j.ress.2003.12.004
  9. Serhat Seker, Emine Ayaz, Erdinc Turkcan, Elman's recurrent neural network applications to condition monitoring in nuclear power plant and rotating machinery, Eng. Appl. Artifi. Intell. 16 (7) (2003) 647-656. https://doi.org/10.1016/j.engappai.2003.10.004
  10. Moshkbar-Bakhshayesh Khalil, Mohammad B. Ghofrani, Transient identification in nuclear power plants: a review, Progr. Nucl. Energy 67 (2013) 23-32. https://doi.org/10.1016/j.pnucene.2013.03.017
  11. Robert E. Uhrig, J. Hines, Computational intelligence in nuclear engineering, Nucl. Eng. Technol. 37.2 (2005) 127-138.
  12. P.F. Fantoni, A. Mazzola, A pattern recognition-artificial neural networks based model for signal validation in nuclear power plants, Ann. Nucl. Energy 23 (13) (1996) 1069-1076. https://doi.org/10.1016/0306-4549(96)84661-5
  13. Mark J. Embrechts, Sandor Benedek, Hybrid identification of nuclear power plant transients with artificial neural networks, IEEE Trans. Ind. Electron. 51 (3) (2004) 686-693. https://doi.org/10.1109/TIE.2004.824874
  14. Seung Jun Lee, Poong Hyun Seong, A dynamic neural network based accident diagnosis advisory system for nuclear power plants, Progr. Nucl. Energy 46 (3-4) (2005) 268-281. https://doi.org/10.1016/j.pnucene.2005.03.009
  15. Kun Mo, Seung Jun Lee, Poong Hyun Seong, A dynamic neural network aggregation model for transient diagnosis in nuclear power plants, Prog. Nucl. Energy 49.3 (2007) 262-272. https://doi.org/10.1016/j.pnucene.2007.01.002
  16. K. Nabeshima, et al., On-line neuro-expert monitoring system for borssele nuclear power plant, Progr. Nucl. Energy 43 (1-4) (2003) 397-404. https://doi.org/10.1016/S0149-1970(03)00051-9
  17. Sepp Hochreiter, Jurgen Schmidhuber, Bridging long time lags by weight guessing and Long Short-Term Memory, Spatiotemporal Models Biol. Artif. Syst. 37 (1996) 65-72.
  18. Sepp Hochreiter, Jurgen Schmidhuber, Long short-term memory, Neural Comput. 9 (8) (1997) 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  19. Michael Auli, Michel Galley, Chris Quirk, Geoffrey Zweig, Joint language and translation modeling with recurrent neural networks, in: Empirical Methods in Natural Language Processing (EMNPL), vol. 3, 2013.
  20. Ilya Sutskever, Oriol Vinyals, Quoc VV. Le, Sequence to sequence learning with neural networks, in: Advances in Neural Information Processing Systems (NIPS), vol. 27, 2014, pp. 3104-3112.
  21. Oriol Vinyals, Alexander Toshev, Samy Bengio, Dumitru Erhan, Show and tell: a neural image caption generator, in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 3156-3164.
  22. Andrej Karpathy, Li Fei-Fei, Deep visual-semantic alignments for generating image descriptions, in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 3128-3137.
  23. Marcus Liwicki, Alex Graves, Horst Bunke, Jurgen Schmidhuber, A novel approach to on-line handwriting recognition based on bidirectional long short-term memory networks, in: Proceedings of the Ninth International Conference on Document Analysis and Recognition, vol. 1, 2007, pp. 367-371.
  24. Gianluca Pollastri, Darisz Przybylski, Burkhard Rost, Pierre Baldi, Improving the prediction of protein secondary structure in three and eight classes using recurrent neural networks and profiles, Proteins Struct. Funct. Bioinform. 47 (2002) 228-235. https://doi.org/10.1002/prot.10082
  25. Jiri Vohradsky, Neural network model of gene expression, FASEB J. 15 (3) (2001) 846-854. https://doi.org/10.1096/fj.00-0361com
  26. Rui Xu, Donald Wunsch II, Ronald Frank, Inference of genetic regulatory networks with recurrent neural network models using particle swarm optimization, IEEE/ACM Trans. Comput. Biol. Bioinform. (TCBB) (2007) 681-692.
  27. Muhammad Subekti, Kazuhiko Kudo, Kunihiko Nabeshima, The development of anomaly diagnosis method using neuro-expert for PWR monitoring system, in: International Conference on Advanced in Nuclear Science and Engineering (ICANSE2007), 2006.
  28. Abiodun Ayodeji, Yong-kuo Liu, Hong Xia, Knowledge base operator support system for nuclear power plant fault diagnosis, Progr. Nucl. Energy 105 (2018) 42-50. https://doi.org/10.1016/j.pnucene.2017.12.013
  29. D. Monner, J.A. Reggia, A generalized LSTM-like training algorithm for secondorder recurrent neural networks, Neural Netw. 25 (2012) 70-83. https://doi.org/10.1016/j.neunet.2011.07.003
  30. C. Lipton, et al., learning to diagnose with LSTM recurrent neural networks, in: International Conference on Learning Representation, Caribe Hilton, San Juan, Puerto Rico, May 2-4, 2016.
  31. James Bergstra, Yoshua Bengio, Random search for hyper-parameter optimization, J. Mach. Learn. Res. (2012) 281-305.
  32. Jasper Snoek, Hugo Larochelle, Ryan P. Adams, Practical bayesian optimization of machine learning algorithms, in: Advances in Neural Information Processing Systems, 2012, pp. 2951-2959.
  33. Christopher M. Bishop, Machine learning and pattern recognition, in: Information Science and Statistics, Springer, Heidelberg, 2006.
  34. Yaguo Lei, et al., An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data, IEEE Trans. Ind. Electron. 63 (5) (2016) 3137-3147. https://doi.org/10.1109/TIE.2016.2519325
  35. Siqin Tao, et al., Bearing fault diagnosismethod based onstacked autoencoder and softmax regression, in: Control Conference (CCC), 2015 34th Chinese, IEEE, 2015.
  36. Kee-Choon Kwon, Jin-Hyung Kim, Accident identification in nuclear power plants using hidden Markov models, Eng. Appl. Artif. Intell. 12 (4) (1999) 491-501. https://doi.org/10.1016/S0952-1976(99)00011-1

피인용 문헌

  1. Analysis of inter-concept dependencies in disease diagnostic cognitive maps using recurrent neural network and genetic algorithms in time series clinical data for targeted treatment vol.10, pp.10, 2018, https://doi.org/10.1007/s12652-018-1116-5
  2. Near Real-Time Global Solar Radiation Forecasting at Multiple Time-Step Horizons Using the Long Short-Term Memory Network vol.13, pp.14, 2020, https://doi.org/10.3390/en13143517
  3. A Sensor Fault-Tolerant Accident Diagnosis System vol.20, pp.20, 2018, https://doi.org/10.3390/s20205839
  4. Rotate Vector (RV) Reducer Fault Detection and Diagnosis System: Towards Component Level Prognostics and Health Management (PHM) vol.20, pp.23, 2018, https://doi.org/10.3390/s20236845
  5. Neural-based time series forecasting of loss of coolant accidents in nuclear power plants vol.160, pp.None, 2018, https://doi.org/10.1016/j.eswa.2020.113699
  6. MODELING NUCLEAR DATA UNCERTAINTIES USING DEEP NEURAL NETWORKS vol.247, pp.None, 2021, https://doi.org/10.1051/epjconf/202124715016
  7. Prediction of the Loss of Feed Water Fault Signatures Using Machine Learning Techniques vol.2021, pp.None, 2018, https://doi.org/10.1155/2021/5511735
  8. A Correlation-Based Feature Selection Algorithm for Operating Data of Nuclear Power Plants vol.2021, pp.None, 2018, https://doi.org/10.1155/2021/9994340
  9. A multi-layer approach to DN 50 electric valve fault diagnosis using shallow-deep intelligent models vol.53, pp.1, 2018, https://doi.org/10.1016/j.net.2020.07.001
  10. Abnormal state diagnosis model tolerant to noise in plant data vol.53, pp.4, 2018, https://doi.org/10.1016/j.net.2020.09.025
  11. Developing a robust and flexible smart tool to predict a full range Critical Heat Flux (CHF) in different LWRs by using deep learning Artificial Neural Networks (ANN) via parallel multi-processing vol.142, pp.None, 2018, https://doi.org/10.1016/j.pnucene.2021.103985
  12. Unsupervised machine learning techniques for fault detection and diagnosis in nuclear power plants vol.142, pp.None, 2018, https://doi.org/10.1016/j.pnucene.2021.103990
  13. Aging detection of plant control system components using recurrent neural network vol.142, pp.None, 2018, https://doi.org/10.1016/j.pnucene.2021.104005
  14. Severe accident in high-power light water reactors: Mitigating strategies, assessment methods and research opportunities vol.143, pp.None, 2018, https://doi.org/10.1016/j.pnucene.2021.104062
  15. Control automation in the heat-up mode of a nuclear power plant using reinforcement learning vol.145, pp.None, 2018, https://doi.org/10.1016/j.pnucene.2021.104107