Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Development of deep autoencoder-based anomaly detection system for HANARO

  • Seunghyoung Ryu (Artificial Intelligence Application & Strategy Team, Korea Atomic Energy Research Institute) ;
  • Byoungil Jeon (Artificial Intelligence Application & Strategy Team, Korea Atomic Energy Research Institute) ;
  • Hogeon Seo (Artificial Intelligence Application & Strategy Team, Korea Atomic Energy Research Institute) ;
  • Minwoo Lee (HANARO Management Division, Korea Atomic Energy Research Institute) ;
  • Jin-Won Shin (HANARO Management Division, Korea Atomic Energy Research Institute) ;
  • Yonggyun Yu (Artificial Intelligence Application & Strategy Team, Korea Atomic Energy Research Institute)
  • Received : 2022.08.18
  • Accepted : 2022.10.09
  • Published : 2023.02.25
Download PDF
⟨ Previous Next ⟩

Abstract

The high-flux advanced neutron application reactor (HANARO) is a multi-purpose research reactor at the Korea Atomic Energy Research Institute (KAERI). HANARO has been used in scientific and industrial research and developments. Therefore, stable operation is necessary for national science and industrial prospects. This study proposed an anomaly detection system based on deep learning, that supports the stable operation of HANARO. The proposed system collects multiple sensor data, displays system information, analyzes status, and performs anomaly detection using deep autoencoder. The system comprises communication, visualization, and anomaly-detection modules, and the prototype system is implemented on site in 2021. Finally, an analysis of the historical data and synthetic anomalies was conducted to verify the overall system; simulation results based on the historical data show that 12 cases out of 19 abnormal events can be detected in advance or on time by the deep learning AD model.

Keywords

Acknowledgement

This research was supported by a grant from the Korea Atomic Energy Research Institute (KAERI) R&D Program (No. KAERI-524450-22).

References

  1. K.N. Choo, M.S. Cho, S.W. Yang, S.J. Park, Contribution of HANARO irradiation technologies to national nuclear R&D, Nucl. Eng. Technol. 46 (4) (2014) 501-512.  https://doi.org/10.5516/NET.07.2014.006
  2. J. Bae, G. Kim, S.J. Lee, Real-time prediction of nuclear power plant parameter trends following operator actions, Expert Syst. Appl. 186 (2021), 115848. 
  3. H. Kim, S. Jo, J. Kim, G. Park, J. Kim, Development of Long-Term prediction algorithm based on component states using BiLSTM and attention mechanism, in: 2021 5th International Conference on System Reliability and Safety (ICSRS), IEEE, 2021, pp. 258-264. 
  4. H. Kim, J. Cho, J. Park, Application of a deep learning technique to the development of a fast accident scenario identifier, IEEE Access 8 (2020) 177363-177373.  https://doi.org/10.1109/ACCESS.2020.3026104
  5. S. Ryu, H. Kim, S.G. Kim, K. Jin, J. Cho, J. Park, Probabilistic deep learning model as a tool for supporting the fast simulation of a thermal-hydraulic code, Expert Syst. Appl. 200 (2022), 116966. 
  6. S.G. Kim, Y.H. Chae, P.H. Seong, Development of a generative adversarial-network-based signal reconstruction method for nuclear power plants, Ann. Nucl. Energy 142 (2020), 107410. 
  7. D. Lee, A.M. Arigi, J. Kim, Algorithm for autonomous power-increase operation using deep reinforcement learning and a rule-based system, IEEE Access 8 (2020) 196727-196746.  https://doi.org/10.1109/ACCESS.2020.3034218
  8. D. Lee, P.H. Seong, J. Kim, Autonomous operation algorithm for safety systems of nuclear power plants by using long-short term memory and function-based hierarchical framework, Ann. Nucl. Energy 119 (2018) 287-299.  https://doi.org/10.1016/j.anucene.2018.05.020
  9. S. Chen, K. Demachi, Proposal of an insider sabotage detection method for nuclear security using deep learning, J. Nucl. Sci. Technol. 56 (7) (2019) 599-607.  https://doi.org/10.1080/00223131.2019.1611501
  10. T.-H. Lin, T.-C. Wang, S.-C. Wu, Deep learning schemes for event identification and signal reconstruction in nuclear power plants with sensor faults, Ann. Nucl. Energy 154 (2021), 108113. 
  11. M.C. dos Santos, V.H.C. Pinheiro, F.S.M. do Desterro, R.K. de Avellar, R. Schirru, A. dos Santos Nicolau, A.M.M. de Lima, Deep rectifier neural network applied to the accident identification problem in a PWR nuclear power plant, Ann. Nucl. Energy 133 (2019) 400-408.  https://doi.org/10.1016/j.anucene.2019.05.039
  12. M.I. Radaideh, C. Pigg, T. Kozlowski, Y. Deng, A. Qu, Neural-based time series forecasting of loss of coolant accidents in nuclear power plants, Expert Syst. Appl. 160 (2020), 113699. 
  13. K. Jin, H. Kim, S. Ryu, S. Kim, J. Park, An approach to constructing effective training data for a classification model to evaluate the reliability of a passive safety system, Reliab. Eng. Syst. Saf. 222 (2022), 108446. 
  14. F. Caliva, F.S. De Ribeiro, A. Mylonakis, C. Demazi'ere, P. Vinai, G. Leontidis, S. Kollias, A deep learning approach to anomaly detection in nuclear reactors, in: 2018 International Joint Conference on Neural Networks (IJCNN), IEEE, 2018, pp. 1-8. 
  15. J. Hou, K. Ni, A. Hawari, An artificial neural network based anomaly detection algorithm for nuclear power plants, Transactions 120 (1) (2019) 219-222. 
  16. S. Lee, J. Kim, Design of computerized operator support system for technical specification monitoring, Ann. Nucl. Energy 165 (2022), 108661. 
  17. J. Ahn, J. Bae, B.J. Min, S.J. Lee, Operation validation system to prevent human errors in nuclear power plants, Nucl. Eng. Des. 397 (2022), 111949. 
  18. K. Nabeshima, T. Suzudo, T. Ohno, K. Kudo, Nuclear reactor monitoring with the combination of neural network and expert system, Math. Comput. Simulat. 60 (3-5) (2002) 233-244.  https://doi.org/10.1016/S0378-4754(02)00018-6
  19. T. Santosh, A. Srivastava, V.S. Rao, A. Ghosh, H. Kushwaha, Diagnostic system for identification of accident scenarios in nuclear power plants using artificial neural networks, Reliab. Eng. Syst. Saf. 94 (3) (2009) 759-762.  https://doi.org/10.1016/j.ress.2008.08.005
  20. G. Lee, S.J. Lee, C. Lee, A convolutional neural network model for abnormality diagnosis in a nuclear power plant, Appl. Soft Comput. 99 (2021), 106874. 
  21. K. Nabeshima, T. Suzudo, K. Suzuki, E. Turkcan, Real-time nuclear power plant monitoring with neural network, J. Nucl. Sci. Technol. 35 (2) (1998) 93-100.  https://doi.org/10.1080/18811248.1998.9733829
  22. T. Tasakos, G. Ioannou, V. Verma, G. Alexandridis, A. Dokhane, A. Stafylopatis, Deep learning-based anomaly detection in nuclear reactor cores, in: Proceedings of the International Conference on Mathematics & Computational Methods Applied to Nuclear Science & Engineering, M&C 2021, Online, 2021, pp. 3-7. 
  23. A. Messai, A. Mellit, I. Abdellani, A.M. Pavan, On-line fault detection of a fuel rod temperature measurement sensor in a nuclear reactor core using ANNs, Prog. Nucl. Energy 79 (2015) 8-21.  https://doi.org/10.1016/j.pnucene.2014.10.013
  24. M. Kim, E. Ou, P.-L. Loh, T. Allen, R. Agasie, K. Liu, RNN-Based online anomaly detection in nuclear reactors for highly imbalanced datasets with uncertainty, Nucl. Eng. Des. 364 (2020), 110699. 
  25. D.P. Kingma, J. Ba, Adam: A Method for Stochastic Optimization, arXiv preprint, 2014 arXiv:1412.6980. 
  26. I. Loshchilov, F. Hutter, SGDR: Stochastic Gradient Descent with Warm Restarts, arXiv preprint, 2016 arXiv:1608.03983. 
  27. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, et al., Pytorch: an imperative style, high-performance deep learning library, Adv. Neural Inf. Process. Syst. 32 (2019). 
  28. S. Ryu, B. Jeon, M. Lee, Y. Yu, Evaluation of deep autoencoder based anomaly detection with cold neutron source facility in HANARO, Transact. Korean Nuclear Soc. Virtual Autumn Meeting 300 (69) (2021) 89. 
  29. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, et al., Scikit-learn: machine learning in python, J. Mach. Learn. Res. 12 (2011) 2825-2830. 
  30. J. Bergstra, R. Bardenet, Y. Bengio, B. Kegl, Algorithms for hyperparameter optimization, Adv. Neural Inf. Process. Syst. 24 (2011). 
  31. J. Bergstra, Y. Bengio, Random search for hyper-parameter optimization, J. Mach. Learn. Res. 13 (2) (2012). 
  32. J. Snoek, H. Larochelle, R.P. Adams, Practical Bayesian optimization of machine learning algorithms, Adv. Neural Inf. Process. Syst. 25 (2012). 
  33. K.H. Kim, S. Shim, Y. Lim, J. Jeon, J. Choi, B. Kim, A.S. Yoon, Rapp: novelty detection with reconstruction along projection pathway, in: International Conference on Learning Representations, 2019. 
  34. S. Ryu, J. Yim, J. Seo, Y. Yu, H. Seo, Quantile autoencoder with abnormality accumulation for anomaly detection of multivariate sensor data, IEEE Access 10 (2022) 70428-70439.  https://doi.org/10.1109/ACCESS.2022.3187426
  35. S. Akcay, A. Atapour-Abarghouei, T.P. Breckon, Ganomaly: semisupervised anomaly detection via adversarial training, in: Asian Conference on Computer Vision, Springer, 2018, pp. 622-637. 
  36. B. Zong, Q. Song, M.R. Min, W. Cheng, C. Lumezanu, D. Cho, H. Chen, Deep autoencoding Gaussian mixture model for unsupervised anomaly detection, in: International Conference on Learning Representations, 2018. 
  37. D.H. Wolpert, Stacked generalization, Neural Network. 5 (2) (1992) 241-259.  https://doi.org/10.1016/S0893-6080(05)80023-1
  38. L. Breiman, Bagging predictors, Mach. Learn. 24 (2) (1996) 123-140.  https://doi.org/10.1007/BF00058655
  39. R.E. Schapire, The Boosting Approach to Machine Learning: an Overview, Nonlinear Estimation and Classification, 2003, pp. 149-171.