Discrimination model using denoising autoencoder-based majority vote classification for reducing false alarm rate
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
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 autoencoderbased 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
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 autoencoderbased 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
참고문헌 (31)
- B. Bechtold, "KUES'95-The modern diagnostic system for loose parts monitoring", Prog. Nucl. Energy, 34(3), pp.221~230 (1999)
- C. W. Mayo, "Loose parts signal theory", Prog. Nucl. Energy, 15, pp.535~543 (1985)
- C. W. Mayo, "Loose-part signal properties", Prog. Nucl. Energy, 28(4), pp.347~357 (1994)
- J. S. Kim, "Development of automatic algorithm for localizing loose parts with a steam generator", Nucl. Eng. Des, 219(3), pp.269~276 (2003)
- Y. W. Chang, "Algorithm automation for nuclear power plant loose parts monitoring system", Nucl. Eng. Des, 231(1), pp.99~107 (2004)
- 신성환, "MASS ESTIMATION OF IMPACTING OBJECTS AGAINST A STRUCTURE USING AN ARTIFICIAL NEURAL NETWORK WITHOUT CONSIDERATION OF BACKGROUND NOISE", Nuclear Engineering and Technology, 43(4), pp.343~354 (2011), 한국원자력학회
- L. X. Fang, "A study on the method of impact mass estimation of loose parts", Prog. Nucl. Energy, 70, pp.242~248 (2014)
- J. Liska, "Localization of loose Part Impacts on the general 3D surface of the nuclear power plant coolant circuit components", Prog. Nucl. Energy, 99, pp.140~146 (2017)
- 문성인, "Model-based localization and mass-estimation methodology of metallic loose parts", Nuclear Engineering and Technology, 52(4), pp.846~855 (2020), 한국원자력학회
- 문성인, "Impact parameter prediction of a simulated metallic loose part using convolutional neural network", Nuclear Engineering and Technology, 53(4), pp.1199~1209 (2021), 한국원자력학회[DOI]
- Y. Choi, "An impact source localization technique for a nuclear power plant by using sensors of different types", ISA Trans, 50(1), pp.111~118 (2011)
- 신성환, "Markov chain-based mass estimation method for loose part monitoring system and its performance", Nuclear Engineering and Technology, 49(7), pp.1555~1562 (2017), 한국원자력학회
- T. Tsunoda, "Studies on the loose part evaluation technique", Prog. Nucl. Energy, 15, pp.569~576 (1985)
- G. L. Zigler, "On-line loose parts monitoring false alarm discrimination", Prog. Nucl. Energy, 15, pp.577~581 (1985)
- C. W. Mayo, "Loose part monitoring system improvements", Prog. Nucl. Energy, 21, pp.505~513 (1988)
- S. Figedy, "Modern methods of signal processing in the loose part monitoring system", Prog. Nucl. Energy, 46(3-4), pp.253~267 (2005)
- J. S. Kim, "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), pp.95~99 (2002)
- Y. Cao, "An alarm method for a loose parts monitoring system", Shock Vib, 19(4), pp.753~761 (2012)
- M. G. Min, "Development of an algorithm to discriminate between valid and false alarms in a loose-parts monitoring system", Nucl. Eng. Des, 278, pp.1~6 (2014)
- J. Yang, "Detection method of loose parts in nuclear reactor based on eigenvector algorithm", Int. J. Fuzzy Logic And Int. Syst. Pro
- J. Meng, "Loose parts detection method combining blind deconvolution with support vector machine", Ann. Nucl. Energy, 149, pp.107782~ (2020)
- J. S. Kim, "An automatic diagnosis method for loose parts monitoring system", ISIE 2001. 2001 IEEE International Symposium on Industrial Electronics Proceedings, 3, pp.1971~1977 (2001), IEEE
- C. Lu, "Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification", Signal Process, 130, pp.377~388 (2017)
- M. Gan, "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, pp.92~104 (2016)
- D. Verstraete, "Deep learning enabled fault diagnosis using time-frequency image analysis of rolling element bearings", Shock Vib (2017)
- H. Shao, "A novel deep autoencoder feature learning method for rotating machinery fault diagnosis", Mech. Syst. Signal Process, 95, pp.187~204 (2017)
- F. Jia, "A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines", Neurocomputing, 272, pp.619~628 (2018)
- W. 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, pp.439~453 (2018)
- H. B. Yang, "Fault diagnosis of reciprocating compressor based on convolutional neural networks with multisource raw vibration signals", Math. Probl Eng (2019)
- P. Vincent, "Extracting and composing robust features with denoising autoencoders", Proceedings of the 25th International Conference on Machine Learning, pp.1096~1103 (2008)
- C. J. Willmott, "Advantages of the mean absolute error(MAE)over the root mean square error(RMSE)in assessing average model performance", Clim. Res, 30(1), pp.79~82 (2005)