Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Discrimination model using denoising autoencoder-based majority vote classification for reducing false alarm rate

  • Heonyong Lee (Department of Mechanical Engineering, Seoul National University) ;
  • Kyungtak Yu (Ace High End Tower, 14, Seongsui-ro 10-gil, Seongdong-gu, Seoul, South Korea) ;
  • Shiu Kim (Hongnong-ro, Hongnong-eup, Yeonggwang-gun, Jeollanam-do, South Korea)
  • Received : 2022.12.27
  • Accepted : 2023.06.21
  • Published : 2023.10.25
Download PDF
⟨ Previous Next ⟩

Abstract

Loose parts monitoring and detecting alarm type in real Nuclear Power Plant have challenges such as background noise, insufficient alarm data, and difficulty of distinction between alarm data that occur during start and stop. Although many signal processing methods and alarm determination algorithms have been developed, it is not easy to determine valid alarm and extract the meaning data from alarm signal including background noise. To address these issues, this paper proposes a denoising autoencoder-based majority vote classification. Training and test data are prepared by acquiring alarm data from real NPP and simulation facility for data augmentation, and noisy data is reproduced by adding Gaussian noise. Using DAEs with 3, 5, 7, and 9 layers, features are extracted for each model and classified into neural networks. Finally, the results obtained from each DAE are classified by majority voting. Also, through comparison with other methods, the accuracy and the false alarm rate are compared, and the excellence of the proposed method is confirmed.

Keywords

Acknowledgement

This work was supported by the Korea Institute of Energy Technology Evaluation and Planning (KETEP) and the Ministry of Trade, Industry & Energy (MOTIE) of the Republic of Korea (No. 20206510100010).

References

  1. B. Bechtold, U. Kunze, KUES'95-The modern diagnostic system for loose parts monitoring, Prog. Nucl. Energy 34 (3) (1999) 221-230. https://doi.org/10.1016/S0149-1970(98)00008-0
  2. C.W. Mayo, Loose parts signal theory, Prog. Nucl. Energy 15 (1985) 535-543. https://doi.org/10.1016/0149-1970(85)90080-0
  3. C.W. Mayo, Loose-part signal properties, Prog. Nucl. Energy 28 (4) (1994) 347-357. https://doi.org/10.1016/0149-1970(94)90011-6
  4. J.S. Kim, I.K. Hwang, J.T. Kim, J. Lyou, Development of automatic algorithm for localizing loose parts with a steam generator, Nucl. Eng. Des. 219 (3) (2003) 269-276. https://doi.org/10.1016/S0029-5493(02)00281-9
  5. Y.W. Chang, J.C. Jung, P.H. Seong, Algorithm automation for nuclear power plant loose parts monitoring system, Nucl. Eng. Des. 231 (1) (2004) 99-107. https://doi.org/10.1016/j.nucengdes.2003.02.001
  6. S.H. Shin, J.H. Park, D.B. Yoon, Y.C. Choi, Mass estimation of impacting objects against a structure using an artificial neural network without consideration of background noise, Nucl. Eng. Technol. 43 (4) (2011) 343-354. https://doi.org/10.5516/NET.2011.43.4.343
  7. L.X. Fang, T.T. Ji, F. Zeng, W. Zhang, Y.C. Xie, C.H. Wang, K.F. Zhang, A study on the method of impact mass estimation of loose parts, Prog. Nucl. Energy 70 (2014) 242-248. https://doi.org/10.1016/j.pnucene.2013.10.004
  8. J. Liska, S. Kunkel, Localization of loose Part Impacts on the general 3D surface of the nuclear power plant coolant circuit components, Prog. Nucl. Energy 99 (2017) 140-146. https://doi.org/10.1016/j.pnucene.2017.05.004
  9. S. Moon, S. Han, T. Kang, S. Han, M. Kim, Model-based localization and mass-estimation methodology of metallic loose parts, Nucl. Eng. Technol. 52 (4) (2020) 846-855. https://doi.org/10.1016/j.net.2019.10.005
  10. S. Moon, S. Han, T. Kang, S. Han, K. Kim, Y. Yu, J. Eom, Impact parameter prediction of a simulated metallic loose part using convolutional neural network, Nucl. Eng. Technol. 53 (4) (2021) 1199-1209. https://doi.org/10.1016/j.net.2020.10.009
  11. Y. Choi, J. Park, K. Choi, An impact source localization technique for a nuclear power plant by using sensors of different types, ISA Trans. 50 (1) (2011) 111-118. https://doi.org/10.1016/j.isatra.2010.08.004
  12. S. Shin, J. Park, D. Yoon, S. Han, T. Kang, Markov chain-based mass estimation method for loose part monitoring system and its performance, Nucl. Eng. Technol. 49 (7) (2017) 1555-1562. https://doi.org/10.1016/j.net.2017.05.005
  13. T. Tsunoda, T. Kato, K. Hirata, Y. Sekido, K. Sendai, M. Segawa, O. Tsuneoka, Studies on the loose part evaluation technique, Prog. Nucl. Energy 15 (1985) 569-576. https://doi.org/10.1016/0149-1970(85)90084-8
  14. G.L. Zigler, G.A. Morris, R.C. Roberts, On-line loose parts monitoring false alarm discrimination, Prog. Nucl. Energy 15 (1985) 577-581. https://doi.org/10.1016/0149-1970(85)90085-X
  15. C.W. Mayo, H.G. Shugars, Loose part monitoring system improvements, Prog. Nucl. Energy 21 (1988) 505-513. https://doi.org/10.1016/0149-1970(88)90070-4
  16. S. Figedy, G. Oksa, Modern methods of signal processing in the loose part monitoring system, Prog. Nucl. Energy 46 (3-4) (2005) 253-267. https://doi.org/10.1016/j.pnucene.2005.03.008
  17. J.S. Kim, I.K. Hwang, J.T. Kim, B.S. Moon, J. Lyou, A study on loose part monitoring system in nuclear power plant based on neural network, International journal of fuzzy logic and intelligent systems 2 (2) (2002) 95-99. https://doi.org/10.5391/IJFIS.2002.2.2.095
  18. Y. Cao, Y. He, H. Zheng, J. Yang, An alarm method for a loose parts monitoring system, Shock Vib. 19 (4) (2012) 753-761. https://doi.org/10.1155/2012/891085
  19. M.G. Min, C.G. Jeong, J.K. Lee, S.H. Jo, H.J. Kim, Development of an algorithm to discriminate between valid and false alarms in a loose-parts monitoring system, Nucl. Eng. Des. 278 (2014) 1-6. https://doi.org/10.1016/j.nucengdes.2014.05.047
  20. J. Yang, B. Yang, M. Liu, Y. Cao, Detection method of loose parts in nuclear reactor based on eigenvector algorithm, Int. J. Fuzzy Logic And Int. Syst. Pro.
  21. J. Meng, Y. Su, S. Xie, Loose parts detection method combining blind deconvolution with support vector machine, Ann. Nucl. Energy 149 (2020), 107782.
  22. J.S. Kim, I.K. Hwang, T.W. Kim, J. Lyou, An automatic diagnosis method for loose parts monitoring system, in: ISIE 2001. 2001 IEEE International Symposium on Industrial Electronics Proceedings (Cat. No. 01TH8570), vol. 3, IEEE, 2001, pp. 1971-1977.
  23. C. Lu, Z.Y. Wang, W.L. Qin, J. Ma, Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification, Signal Process. 130 (2017) 377-388. https://doi.org/10.1016/j.sigpro.2016.07.028
  24. M. Gan, C. Wang, Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings, Mech. Syst. Signal Process. 72 (2016) 92-104. https://doi.org/10.1016/j.ymssp.2015.11.014
  25. D. Verstraete, A. Ferrada, E.L. Droguett, V. Meruane, M. Modarres, Deep learning enabled fault diagnosis using time-frequency image analysis of rolling element bearings, Shock Vib. (2017).
  26. H. Shao, H. Jiang, H. Zhao, F. Wang, A novel deep autoencoder feature learning method for rotating machinery fault diagnosis, Mech. Syst. Signal Process. 95 (2017) 187-204. https://doi.org/10.1016/j.ymssp.2017.03.034
  27. F. Jia, Y. Lei, L. Guo, J. Lin, S. Xing, A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines, Neurocomputing 272 (2018) 619-628. https://doi.org/10.1016/j.neucom.2017.07.032
  28. W. Zhang, C. Li, G. Peng, Y. Chen, Z. Zhang, A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load, Mech. Syst. Signal Process. 100 (2018) 439-453. https://doi.org/10.1016/j.ymssp.2017.06.022
  29. H.B. Yang, J.A. Zhang, L.L. Chen, H.L. Zhang, S.L. Liu, Fault diagnosis of reciprocating compressor based on convolutional neural networks with multisource raw vibration signals, Math. Probl Eng. (2019).
  30. P. Vincent, H. Larochelle, Y. Bengio, P.A. Manzagol, Extracting and composing robust features with denoising autoencoders, in: Proceedings of the 25th International Conference on Machine Learning, 2008, pp. 1096-1103.
  31. C.J. Willmott, K. Matsuura, Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance, Clim. Res. 30 (1) (2005) 79-82. https://doi.org/10.3354/cr030079