Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Relative humidity prediction of a leakage area for small RCS leakage quantification by applying the Bi-LSTM neural networks

  • Sang Hyun Lee (Department of Nuclear Engineering, Chosun University) ;
  • Hye Seon Jo (Department of Nuclear Engineering, Chosun University) ;
  • Man Gyun Na (Department of Nuclear Engineering, Chosun University)
  • Received : 2023.06.06
  • Accepted : 2023.12.10
  • Published : 2024.05.25
Download PDF
⟨ Previous Next ⟩

Abstract

In nuclear power plants, reactor coolant leakage can occur due to various reasons. Early detection of leaks is crucial for maintaining the safety of nuclear power plants. Currently, a detection system is being developed in Korea to identify reactor coolant system (RCS) leakage of less than 0.5 gpm. Typically, RCS leaks are detected by monitoring temperature, humidity, and radioactivity in the containment, and a water level in the sump. However, detecting small leaks proves challenging because the resulting changes in the containment humidity and temperature, and the sump water level are minimal. To address these issues and improve leak detection speed, it is necessary to quantify the leaks and develop an artificial intelligence-based leak detection system. In this study, we employed bidirectional long short-term memory, which are types of neural networks used in artificial intelligence, to predict the relative humidity in the leakage area for leak quantification. Additionally, an optimization technique was implemented to reduce learning time and enhance prediction performance. Through evaluation of the developed artificial intelligence model's prediction accuracy, we expect it to be valuable for future leak detection systems by accurately predicting the relative humidity in a leakage area.

Keywords

Acknowledgement

This work was supported by the Korea Institute of Energy Technology Evaluation and Planning (KETEP) grant funded by the Korea government (MOTIE) (Grant No. 20211510100050, Development of a real-time detection system for unidentified RCS leakage less than 0.5gpm).

References

  1. Korea Institute of Nuclear Safety, Reports of Accident and Breakdown in the Nuclear Power Plant, Korea Institute of Nuclear Safety, 2009, 170327K4. 
  2. Operational Performance Information System for Nuclear Power Plant, Nuclear accident and failure status. http://opis.kins.re.kr/opis?act=KROBA3100R last modified Jan 05, 2023, accessed January 16, 2023. 
  3. Y.S. Kim, D.J. Euh, W.S. Kim, T.S. Kwon, Investigation of leakage characteristics on major equipment/component in reactor system, The KSFM Journal of Fluid Machinery 22 (2019) 30-35. 
  4. S. Hochreiter, J. Schmidhuber, Long short-term memory, Neural Comput. 9 (1997) 1735-1780.  https://doi.org/10.1162/neco.1997.9.8.1735
  5. M. Schuster, K.K. Paliwal, Bidirectional recurrent neural networks, IEEE Trans. Signal Process. 45 (1997) 2673-2681.  https://doi.org/10.1109/78.650093
  6. H.S. Jo, J.H. Park, M.G. Na, Prediction of Relative Humidity Injected into the Sensor Tube of an RCPB Leakage Detection System Using Artificial Intelligence, Korean Nuclear Society Virtual Autumn Meeting, 2021. 
  7. J. Bergstra, Y. Bengio, Random search for hyper-parameter optimization, J. Mach. Learn. Res. 13 (2012) 281-305. 
  8. J.J. Jung, H.Y. Yun, I.K. Park, H.G. Jo, The CUPID CODE development and assessment strategy, Nucl. Eng. Technol. 42 (2010) 636-655.  https://doi.org/10.5516/NET.2010.42.6.636
  9. T.S. Kwon, J.R. Kim, C.K. Choi, J.S. Park, C.R. Choi, Development of an unidentified RCS leakage detection sensor system less than 0.5 gpm, The KSFM Journal of Fluid Machinery 24 (2021) 13-19.  https://doi.org/10.5293/kfma.2021.24.2.013
  10. S.J. Park, J.K. Park, G.Y. Heo, Transient diagnosis and prognosis for secondary system in nuclear power plants, Nucl. Eng. Technol. 48 (2016) 1184-1191.  https://doi.org/10.1016/j.net.2016.03.009
  11. Y.D. Koo, Y.J. An, C.H. Kim, M.G. Na, Nuclear reactor vessel water level prediction during severe accidents using deep neural networks, Nucl. Eng. Technol. 51 (2019) 723-730.  https://doi.org/10.1016/j.net.2018.12.019
  12. H.M. Park, J.H. Lee, K.D. Kim, Wall temperature prediction at critical heat flux using a machine learning model, Ann. Nucl. Energy 141 (2020). 
  13. H.S. Jo, Y.D. Koo, J.H. Park, S.W. Oh, C.H. Kim, M.G. Na, Prediction of golden time for recovering SISs using deep fuzzy neural networks with rule-dropout, Nucl. Eng. Technol. 53 (2021) 4014-4021.  https://doi.org/10.1016/j.net.2021.06.017
  14. H.J. Kim, J.H. Kim, Lonh-term prediction of safety parameters with uncertainty estimation in emergency situations at nuclear power plants, Eng. Technol. 55 (2023) 1630-1643. 
  15. T. Tasakos, G. Ioannou, V. Verma, G. Alexandridis, A. Dokhane, A. Stafylopatis, Deep learning-based anomaly detection in nuclear rector cores, in: Proceedings of the International Conference on Mathematics & Computational Methods Applied to Nuclear Science & Engineering (M&C 2021), 2021. 
  16. Y.H. Choi, G.M. Yoon, J.H. Kim, Unsupervised learning algorithm for signal validation in emergency situation at nuclear power plants, Nucl. Eng. Technol. 54 (2022) 1230-1244.  https://doi.org/10.1016/j.net.2021.10.006
  17. K.H. Yoo, H. J, Back, M.G. Na, S. Hur, H.M. Kim, Smart support system for diagnosing severe accidents in nuclear power plants, Nucl. Eng. Technol. 50 (2018) 562-569.  https://doi.org/10.1016/j.net.2018.03.007
  18. J. She, T. Shi, S. Xue, Y. Zhu, S. Lu, P. Sun, H. Cao, Diagnosis and prediction for loss of coolant accidents in nuclear power plants using deep learning methods, Front. Energy Res. 9 (2021) 1-9. 
  19. D.I. Lee, P.H. Seong, J.H. 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
  20. J.Y. Bae, J.M. Lee, S.J. Lee, Deep reinforcement learning for a multi-objective operation in a nuclear power plant, Nucl. Eng. Technol. 55 (2023) 3277-3290. 
  21. J.H. Park, H.S. Jo, S.H. Lee, S.W. Oh, M.G. Na, A reliable intelligent diagnostic assistant for nuclear power plants using explainable artificial intelligence of GRUAE, LightGBM and SHAP, Nucl. Eng. Technol. 54 (2022) 1271-1287.  https://doi.org/10.1016/j.net.2021.10.024
  22. J.H. Shin, J.Y. Bae, J.M. Kim, S.J. Lee, An interpretable convolutional neural network for nuclear power plant abnormal events, Appl. Soft Comput. 133 (2023) 1-16. 
  23. Y. Fu, D. Zhang, Y. Xiao, Z. Wang, H. Zhou, An interpretable time series data prediction framework for severe accidents in nuclear power plants, Entropy 25 (2023) 1-18. 
  24. Vaisala Oyj, Calculation Formulas for Humidity-Humidity Conversion Formulas; Vaisala, Finland, Helsinki, 2013. 
  25. C.K. Koc, Analysis of sliding window techniques for exponentiation, Comput. Math. Appl. 30 (1995) 17-24.  https://doi.org/10.1016/0898-1221(95)00153-P
  26. S. Ruder, An Overview of Gradient Descent Optimization Algorithms, 2016 arXiv preprint arXiv:1609.04747. 
  27. D.P. Kingma, J.L. Ba, Adam: A Method for Stochastic Optimization, 2014 arXiv preprint arXiv:1412.6980.