Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

RNN-based integrated system for real-time sensor fault detection and fault-informed accident diagnosis in nuclear power plant accidents

  • Jeonghun Choi (Ulsan National Institute of Science and Technology) ;
  • Seung Jun Lee (Ulsan National Institute of Science and Technology)
  • Received : 2022.05.16
  • Accepted : 2022.10.25
  • Published : 2023.03.25
Download PDF
⟨ Previous Next ⟩

Abstract

Sensor faults in nuclear power plant instrumentation have the potential to spread negative effects from wrong signals that can cause an accident misdiagnosis by plant operators. To detect sensor faults and make accurate accident diagnoses, prior studies have developed a supervised learning-based sensor fault detection model and an accident diagnosis model with faulty sensor isolation. Even though the developed neural network models demonstrated satisfactory performance, their diagnosis performance should be reevaluated considering real-time connection. When operating in real-time, the diagnosis model is expected to indiscriminately accept fault data before receiving delayed fault information transferred from the previous fault detection model. The uncertainty of neural networks can also have a significant impact following the sensor fault features. In the present work, a pilot study was conducted to connect two models and observe actual outcomes from a real-time application with an integrated system. While the initial results showed an overall successful diagnosis, some issues were observed. To recover the diagnosis performance degradations, additive logics were applied to minimize the diagnosis failures that were not observed in the previous validations of the separate models. The results of a case study were then analyzed in terms of the real-time diagnosis outputs that plant operators would actually face in an emergency situation.

Keywords

Acknowledgement

This work was supported by a National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (No.NRF-2018M2B2B1065653 and No.RS-2022-00144042).

References

  1. Juan Pablo Usuga Cadavid, et al., Machine learning applied in production planning and control: a state-of-the-art in the era of industry 4.0, J. Intell. Manuf. 31 (2020) 1531-1558, 6. https://doi.org/10.1007/s10845-019-01531-7
  2. A.C. Cilliers, Benchmarking an expert fault detection and diagnostic system on the Three Mile Island accident event sequence, Ann. Nucl. Energy 62 (2013) 326-332. https://doi.org/10.1016/j.anucene.2013.06.037
  3. Jeonghun Choi, Seung Jun Lee, Consistency index-based sensor fault detection system for nuclear power plant emergency situations using an LSTM network, Sensors 20 (2020) 1651, 6.
  4. Jeonghun Choi, Seung Jun Lee, A sensor fault-tolerant accident diagnosis system, Sensors 20 (2020) 5839.
  5. Wei Li, Minjun Peng, Qingzhong Wang, Improved PCA method for sensor fault detection and isolation in a nuclear power plant, Nucl. Eng. Technol. 51 (2019) 146-154, 1. https://doi.org/10.1016/j.net.2018.08.020
  6. Ting-Han Lin, Shun-Chi Wu, Sensor fault detection, isolation and reconstruction in nuclear power plants, Ann. Nucl. Energy 126 (2019) 398-409. https://doi.org/10.1016/j.anucene.2018.11.044
  7. Jamie B. Coble, et al., A Review of Sensor Calibration Monitoring for Calibration Interval Extension in Nuclear Power Plants, 2012.
  8. Younhee Choi, Gyeongmin Yoon, Jonghyun Kim, Unsupervised learning algorithm for signal validation in emergency situations at nuclear power plants, Nucl. Eng. Technol. 54 (4) (2022) 1230-1244. https://doi.org/10.1016/j.net.2021.10.006
  9. 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
  10. Silvia Tolo, et al., Robust on-line diagnosis tool for the early accident detection in nuclear power plants, Reliab. Eng. Syst. Saf. 186 (2019) 110-119. https://doi.org/10.1016/j.ress.2019.02.015
  11. Abiodun Ayodeji, Yong-kuo Liu, Hong Xia, Knowledge base operator support system for nuclear power plant fault diagnosis, Prog. Nucl. Energy 105 (2018) 42-50. https://doi.org/10.1016/j.pnucene.2017.12.013
  12. Alexandre Evsukoff, Sylviane Gentil, Recurrent neuro-fuzzy system for fault detection and isolation in nuclear reactors, Adv. Eng. Inf. 19 (2005) 55-66, 1. https://doi.org/10.1016/j.aei.2005.01.009
  13. Hang Wang, et al., Advanced fault diagnosis method for nuclear power plant based on convolutional gated recurrent network and enhanced particle swarm optimization, Ann. Nucl. Energy 151 (2021), 107934.
  14. Piero Baraldi, et al., Comparison of data-driven reconstruction methods for fault detection, IEEE Trans. Reliab. 64 (2015) 852-860, 3. https://doi.org/10.1109/TR.2015.2436384
  15. Jaemin Yang, Jonghyun Kim, An accident diagnosis algorithm using long short-term memory, Nucl. Eng. Technol. 50 (2018) 582-588, 4. https://doi.org/10.1016/j.net.2018.03.010
  16. Zhengping Che, et al., Recurrent neural networks for multivariate time series with missing values, Sci. Rep. 8 (2018) 1-12, 1.
  17. Kee-Choon Kwon, et al., Compact Nuclear Simulator and its Upgrade Plan, Korea Atomic energy institute, 1997.
  18. Jae Chang Park, et al., Equipment and Performance Upgrade of Compact Nuclear simulator." No. KAERI/RR-1856/98, Korea Atomic Energy Research Institute, Daejeon, Korea, 1998.
  19. J. Miettinen, et al., Oscillations of single-phase natural circulation during overcooling transients, in: Anticipated and abnormal transients in nuclear power plants., ANS, 1987.
  20. J. Miettinen, Development and assessment of the SBLOCA code SMABRE, in: Proceedings of the CSNI Specialists' Meeting on Small Break LOCA Analyses in LWRs, 1985. Pisa, Italy.
  21. Sana Ullah Jan, Young Doo Lee, Soo Koo, A distributed sensor-fault detection and diagnosis framework using machine learning, Inf. Sci. 547 (2021) 777-796. https://doi.org/10.1016/j.ins.2020.08.068
  22. Eliahu Khalastchi, Meir Kalech, Lior Rokach, Sensor fault detection and diagnosis for autonomous systems, in: Proceedings of the 2013 International Conference on Autonomous Agents and Multi-Agent Systems, 2013.
  23. Ansari Ahmad, Dennis S. Bernstein, Aircraft sensor fault detection using state and input estimation, in: 2016 American Control Conference (ACC), IEEE, 2016.
  24. Jung Sung Kang, Seung Jun Lee, Concept of an intelligent operator support system for initial emergency responses in nuclear power plants, Nucl. Eng. Technol. 54 (7) (2022) 2453-2466. https://doi.org/10.1016/j.net.2022.02.010
  25. Junyong Bae, Geunhee Kim, Seung Jun Lee, Real-time prediction of nuclear power plant parameter trends following operator actions, Expert Syst. Appl. 186 (2021), 115848.
  26. Jonghyun Kim, et al., Conceptual design of autonomous emergency operation system for nuclear power plants and its prototype, Nucl. Eng. Technol. 52 (2020) 308-322, 2. https://doi.org/10.1016/j.net.2019.09.016