Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Event diagnosis method for a nuclear power plant using meta-learning

  • Hee-Jae Lee (Chosun University) ;
  • Daeil Lee (Korea Atomic Energy Research Institute) ;
  • Jonghyun Kim (Chosun University)
  • Received : 2023.06.09
  • Accepted : 2024.01.05
  • Published : 2024.06.25
Download PDF
⟨ Previous Next ⟩

Abstract

Artificial intelligence (AI) techniques are now being considered in the nuclear field, but application faces with the lack of actual plant data. For this reason, most previous studies on AI applications in nuclear power plants (NPPs) have relied on simulators or thermal-hydraulic codes to mimic the plants. However, it remains uncertain whether an AI model trained using a simulator can properly work in an actual NPP. To address this issue, this study suggests the use of metadata, which can give information about parameter trends. Referred to here as robust AI, this concept started with the idea that although the absolute value of a plant parameter differs between a simulator and actual NPP, the parameter trend is identical under the same scenario. Based on the proposed robust AI, this study designs an event diagnosis algorithm to classify abnormal and emergency scenarios in NPPs using prototypical learning. The algorithm was trained using a simulator referencing a Westinghouse 990 MWe reactor and then tested in different environments in Advanced Power Reactor 1400 MWe simulators. The algorithm demonstrated robustness with 100 % diagnostic accuracy (117 out of 117 scenarios). This indicates the potential of the robust AI-based algorithm to be used in actual plants.

Keywords

Acknowledgement

This work was supported by National Research Foundation of Korea (NRF) grants funded by the Korean government (MSIT) (No. RS-2022-00144042 and No. RS-2022-00144150).

References

  1. M.-H. Hsieh, S.-L. Hwang, K.-H. Liu, S.-F.M. Liang, C.-F. Chuang, A decision support system for identifying abnormal operating procedures in a nuclear power plant, Nucl. Eng. Des. 249 (2012) 413-418.
  2. J. Noyes, M. Bransby, People in Control: Human Factors in Control Room Design, Computer Supported Cooperative Work, 2001.
  3. D.N. Hogg, K. Folles, F. Strand-Volden, B. Torralba, Development of a situation awareness measure to evaluate advanced alarm systems in nuclear power plant control rooms, Ergonomics 38 (1995) 2394-2413.
  4. Y. Hirotsu, K. Suzuki, M. Kojima, K. Takano, Multivariate analysis of human error incidents occurring at nuclear power plants: several occurrence patterns of observed human errors, Cognit. Technol. Work 3 (2001) 82-91.
  5. D.Y. Kim, J. Kim, How does a change in the control room design affect diagnostic strategies in nuclear power plants? J. Nucl. Sci. Technol. 51 (2014) 1288-1310.
  6. J.M. O'Hara, W.S. Brown, Nuclear power plant alarm systems: problems and issues, in: Proceedings of the Human Factors Society Annual Meeting, Los Angeles, United States, 1991.
  7. Y. Choi, G. Yoon, J. Kim, Unsupervised learning algorithm for signal validation in emergency situations at nuclear power plants, Nucl. Eng. Technol. 54 (2022) 1230-1244.
  8. J. Kim, S.J. Lee, P.H. Seong, Autonomous Nuclear Power Plants with Artificial Intelligence, Springer International Publishing, 2023.
  9. Z. Guo, R.E. Uhrig, Use of artificial neural networks to analyze nuclear power plant performance, Nucl. Technol. 99 (1992) 36-42.
  10. J. Kim, D. Lee, J. Yang, S. Lee, Conceptual design of autonomous emergency operation system for nuclear power plants and its prototype, Nucl. Eng. Technol. 52 (2020) 308-322.
  11. R.E. Uhrig, Potential application of neural networks to the operation of nuclear power plants, Nucl. Saf. 32 (1991) 68-79.
  12. P. Fantoni, A. Mazzola, A pattern recognition-artificial neural networks based model for signal validation in nuclear power plants, Ann. Nucl. Energy 23 (1996) 1069-1076.
  13. E.B. Bartlett, R.E. Uhrig, Nuclear power plant status diagnostics using an artificial neural network, Nucl. Technol. 97 (1992) 272-281.
  14. S.J. Lee, P.H. Seong, A dynamic neural network based accident diagnosis advisory system for nuclear power plants, Prog. Nucl. Energy 46 (2005) 268-281.
  15. T.V. Santosh, G. Vinod, R.K. Saraf, A.K. Ghosh, H.S. Kushwaha, Application of artificial neural networks to nuclear power plant transient diagnosis, Reliab. Eng. Syst. Saf. 92 (2007) 1468-1472.
  16. C.M. Rocco S, E. Zio, A support vector machine integrated system for the classification of operation anomalies in nuclear components and systems, Reliab. Eng. Syst. Saf. 92 (2007) 593-600.
  17. L. Yong-kuo, A. Abiodun, W. Zhi-bin, W. Mao-pu, P. Min-jun, Y. Wei-feng, A cascade intelligent fault diagnostic technique for nuclear power plants, J. Nucl. Sci. Technol. 55 (2018) 254-266.
  18. J.M. Kim, G. Lee, C. Lee, S.J. Lee, Abnormality diagnosis model for nuclear power plants using two-stage gated recurrent units, Nucl. Eng. Technol. 52 (2020) 2009-2016.
  19. J. Yang, J. Kim, Accident diagnosis algorithm with untrained accident identification during power-increasing operation, Reliab. Eng. Syst. Saf. 202 (2020) 107032.
  20. 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.
  21. H. Kim, A.M. Arigi, J. Kim, Development of a diagnostic algorithm for abnormal situations using long short-term memory and variational autoencoder, Ann. Nucl. Energy 153 (2021) 108077.
  22. Y.H. Chae, C. Lee, S.M. Han, P.H. Seong, Graph neural network based multiple accident diagnosis in nuclear power plants: data optimization to represent the system configuration, Nucl. Eng. Technol. 54 (2022) 2859-2870.
  23. J.H. Purba, Fuzzy probability on reliability study of nuclear power plant probabilistic safety assessment: a review, Prog. Nucl. Energy 76 (2014) 73-80.
  24. B. Qi, X. Xiao, J. Liang, L.C. Po, L. Zhang, J. Tong, An open time-series simulated dataset covering various accidents for nuclear power plants, Sci. Data 9 (2022).
  25. E. Ntoutsi, et al., Bias in data-driven artificial intelligence systems-an introductory survey, Wiley Interdiscip. Rev. Data. Min. Knowl. Discov. 10 (2020).
  26. R. Vilalta, Y. Drissi, A perspective view and survey of meta-learning, Artif. Intell. Rev. 18 (2002) 77-95.
  27. T.M. Hospedales, A. Antoniou, P. Micaelli, A.J. Storkey, Meta-learning in neural networks: a survey, in: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.
  28. J. Vanschoren, Meta-Learning, Automated Machine Learning, Springer, Cham, 2019, pp. 35-61.
  29. S. Chopra, R. Hadsell, Y. LeCun, Learning a similarity metric discriminatively, with application to face verification, in: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San diego, United States, June 20-25, 2005.
  30. G. Koch, R. Zemel, R. Salakhutdinov, Siamese neural networks for one-shot image recognition, in: ICML Deep Learning Workshop, 2015.
  31. O. Vinyals, C. Blundell, T. Lillicrap, D. Wierstra, Matching networks for one shot learning, Adv. Neural Inf. Process. Syst. 29 (2016).
  32. J. Snell, K. Swersky, R. Zemel, Prototypical networks for few-shot learning, Adv. Neural Inf. Process. Syst. 30 (2017).
  33. F. Sung, Y. Yang, L. Zhang, T. Xiang, P.H. Torr, T.M. Hospedales, Learning to compare: relation network for few-shot learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 1199-1208.
  34. Z. Zhan, J. Zhou, B. Xu, Fabric defect classification using prototypical network of few-shot learning algorithm, Comput. Ind. 138 (2022) 103628.
  35. T. Gao, X. Han, Z. Liu, M. Sun, Hybrid attention-based prototypical networks for noisy few-shot relation classification, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2019, pp. 6407-6414.
  36. G. Guibon, M. Labeau, H. Flamein, L. Lefeuvre, C. Clavel, Few-shot emotion recognition in conversation with sequential prototypical networks, Software Impacts 12 (2021) 100237.
  37. K. Wang, J.H. Liew, Y. Zou, D. Zhou, J. Feng, Panet, Few-shot image semantic segmentation with prototype alignment, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 9197-9206, 2019.
  38. Y. Song, T. Wang, S.K. Mondal, J.P. Sahoo, A comprehensive survey of few-shot learning: evolution, applications, challenges, and opportunities, ACM Comput. Surv. Just (February 2023).
  39. Advanced Compact Nuclear Simulator Textbook, Nuclear Training Center in Korea Atomic Energy Research Institute, 1990.
  40. A. Ess, T. Muller, H. Grabner, L. Van Gool, Segmentation-based urban traffic scene understanding, in: Proceedings of the British Machine Vision Conference, London, United Kingdom, Sep 7-10, 2009.
  41. M. Oeljeklaus, F. Hoffmann, T. Bertram, A combined recognition and segmentation model for urban traffic scene understanding, in: IEEE 20th International Conference on Intelligent Transportation Systems, 2017.
  42. M.A. Sotelo, F.J. Rodriguez, L. Magdalena, L.M. Bergasa, L. Boquete, A color vision-based lane tracking system for autonomous driving on unmarked roads, Aut. Robots 16 (2004) 95-116.
  43. Pctran Generic Pressurized Water Reactor Simulator Exercise Handbook, International Atomic Energy Agency, 2019. IAEA-TCS-68.
  44. Y.-H. Cheng, C. Shih, S.-C. Chiang, T.-L. Weng, Introducing pctran as an evaluation tool for nuclear power plant emergency responses, Ann. Nucl. Energy 40 (2012) 122-129.
  45. S.H. Kim, H.H. Kim, I.H. Song, E.Y. Hong, Y.T. Oh, Development of the Nuclear Plant Analyzer for Korean Standard Nuclear Power Plants, 2000. KINS/HR-346.