DOI QR코드

DOI QR Code

A multi-layer approach to DN 50 electric valve fault diagnosis using shallow-deep intelligent models

  • Liu, Yong-kuo (State Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment) ;
  • Zhou, Wen (Fundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University) ;
  • Ayodeji, Abiodun (Fundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University) ;
  • Zhou, Xin-qiu (Fundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University) ;
  • Peng, Min-jun (Fundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University) ;
  • Chao, Nan (Fundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University)
  • Received : 2020.01.09
  • Accepted : 2020.07.03
  • Published : 2021.01.25

Abstract

Timely fault identification is important for safe and reliable operation of the electric valve system. Many research works have utilized different data-driven approach for fault diagnosis in complex systems. However, they do not consider specific characteristics of critical control components such as electric valves. This work presents an integrated shallow-deep fault diagnostic model, developed based on signals extracted from DN50 electric valve. First, the local optimal issue of particle swarm optimization algorithm is solved by optimizing the weight search capability, the particle speed, and position update strategy. Then, to develop a shallow diagnostic model, the modified particle swarm algorithm is combined with support vector machine to form a hybrid improved particle swarm-support vector machine (IPs-SVM). To decouple the influence of the background noise, the wavelet packet transform method is used to reconstruct the vibration signal. Thereafter, the IPs-SVM is used to classify phase imbalance and damaged valve faults, and the performance was evaluated against other models developed using the conventional SVM and particle swarm optimized SVM. Secondly, three different deep belief network (DBN) models are developed, using different acoustic signal structures: raw signal, wavelet transformed signal and time-series (sequential) signal. The models are developed to estimate internal leakage sizes in the electric valve. The predictive performance of the DBN and the evaluation results of the proposed IPs-SVM are also presented in this paper.

Keywords

Acknowledgement

This paper is funded by the Project for State Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment (No.K-A2019.418), the Technical Support Project for Suzhou Nuclear Power Research Institute (SNPI, No.029-GN-b-2018-C45-P.0.99-00003), The Basic Research Project (No. JCKY2017xx7B019) and the Foundation of Science and Technology on Reactor System Design Laboratory (No. HT-KFKT-14-2017003).

References

  1. A. Ayodeji, Y.-k. Liu, Support vector ensemble for incipient fault diagnosis in nuclear plant components, Nucl. Eng. Technol. 50 (2018) 1306-1313. https://doi.org/10.1016/j.net.2018.07.013
  2. M. Peng, et al., An intelligent hybrid methodology of on-line system-level fault diagnosis for nuclear power plant, Nucl. Eng. Technol. 50 (2018) 396-410. https://doi.org/10.1016/j.net.2017.11.014
  3. A. Ayodeji, Y.-k. Liu, H. 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
  4. A. Ayodeji, Y.-k. Liu, PWR heat exchanger tube defects: trends, signatures and diagnostic techniques, Prog. Nucl. Energy 112 (2019) 171-184. https://doi.org/10.1016/j.pnucene.2018.12.017
  5. Z. Guo, et al., Defect detection of nuclear fuel assembly based on deep neural network, Ann. Nucl. Energy 137 (2019) 107078.
  6. K. Ryu, et al., Pipe thinning model development for direct current potential drop data with machine learning approach, Nucl. Eng. Technol. 52 (2020) 784-790. https://doi.org/10.1016/j.net.2019.10.004
  7. J. Zhang, et al., Application of cost-sensitive LSTM in water level prediction for nuclear reactor pressurizer, Nucl. Eng. Technol. 52 (2020) 1429-1435. https://doi.org/10.1016/j.net.2019.12.025
  8. J. Park, et al., MRPC eddy current flaw classification in tubes using deep neural networks, Nucl. Eng. Technol. 51 (2019) 1784-1790. https://doi.org/10.1016/j.net.2019.05.011
  9. J. Liu, et al., Nuclear power plant components condition monitoring by probabilistic support vector machine, Ann. Nucl. Energy 56 (2013) 23-33. https://doi.org/10.1016/j.anucene.2013.01.005
  10. H.A. Gohel, et al., Predictive maintenance architecture development for nuclear infrastructure using machine learning, Nucl. Eng. Technol. 52 (2020) 1436-1442. https://doi.org/10.1016/j.net.2019.12.029
  11. A. Ayodeji, Y.-k. Liu, SVR optimization with soft computing algorithms for incipient SGTR diagnosis, Ann. Nucl. Energy 121 (2018) 89-100. https://doi.org/10.1016/j.anucene.2018.07.011
  12. Z. Yangping, Z. Bingquan, W. DongXin, Application of genetic algorithms to fault diagnosis in nuclear power plants, Reliab. Eng. Syst. Saf. 67 (2000) 153-160. https://doi.org/10.1016/S0951-8320(99)00061-7
  13. B. Yang, et al., Application of total variation denoising in nuclear power plant signal pre-processing, Ann. Nucl. Energy 135 (2020) 106981. https://doi.org/10.1016/j.anucene.2019.106981
  14. J. Jiao, et al., Hierarchical discriminating sparse coding for weak fault feature extraction of rolling bearings, Reliab. Eng. Syst. Saf. 184 (2019) 41-54. https://doi.org/10.1016/j.ress.2018.02.010
  15. J. Yang, J. Kim, An accident diagnosis algorithm using long short-term memory, Nucl. Eng. Technol. 50 (2018) 582-588. https://doi.org/10.1016/j.net.2018.03.010
  16. Y. Liu, et al., A cascade intelligent fault diagnostic technique for nuclear power plants, J. Nucl. Sci. Technol. 55 (2018) 254-266. https://doi.org/10.1080/00223131.2017.1394228
  17. A.R. Marklund, F. Michel, Application of a new passive acoustic leak detection approach to recordings from the Dounreay prototype fast reactor, Ann. Nucl. Energy 85 (2015) 175-182. https://doi.org/10.1016/j.anucene.2015.05.010
  18. W. Hwang, et al., Acoustic emission characteristics of stress corrosion cracks in a type 304 stainless steel tube, Nucl. Eng. Technol. 47 (2015) 454-460. https://doi.org/10.1016/j.net.2015.04.001
  19. Z.W. Jianguo, Support vector machine modeling and its intelligent optimization, in: Proceeding of International Conference on Information Computing and Automation Beijing, China, 2008. April 25-28.
  20. F. Van den Bergh, A.P. Engelbrecht, A study of particle swarm optimization particle trajectories, Inf. Sci. 176 (2006) 937-971. https://doi.org/10.1016/j.ins.2005.02.003
  21. M. Guo, et al., Research on an integrated ICA-SVM based framework for fault diagnosis, in: SMC'03 Conference Proceedings. IEEE International Conference on Systems, Man and Cybernetics. Conference Theme-System Security and Assurance, Washington DC, USA, 2003, 8-8 October.
  22. L.Y. Jianwei, L. Xionglin, Research and development on deep learning, J. Comput. Appl. 31 (2014) 1922-1928.
  23. Y. Chen, D.-Q. Zheng, et al., Chinese relation extraction based on deep belief nets, Ruanjian Xuebao/J. Softw. 23 (2012) 2572-2585.
  24. Z.J. Licheng, et al., Deep Learning, Optimization and recognition(Chinese), Tsinghua University Press, Beijing, 2017, p. 58.
  25. C. Guoliang, Condition Recognition and Quantitative Analysis of Internal Leaks through Valves Based on Acoustic Emission Method (Chinese), China University of Petroleum Press, 2014, p. 17.
  26. A. Ayodeji, et al., Acoustic signal-based leak size estimation for electric valves using deep belief network, 5th International Conference on Computer and Communications (ICCC), Chengdu, China, Dec 6-9, 2019.