Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Research on unsupervised condition monitoring method of pump-type machinery in nuclear power plant

  • Jiyu Zhang (Key Laboratory of Nuclear Safety and Advanced Nuclear Energy Technology, Ministry of Industry and Information Technology, Harbin Engineering University) ;
  • Hong Xia (Key Laboratory of Nuclear Safety and Advanced Nuclear Energy Technology, Ministry of Industry and Information Technology, Harbin Engineering University) ;
  • Zhichao Wang (Department of Radiotherapy, First Affiliated Hospital of Yangtze University) ;
  • Yihu Zhu (Key Laboratory of Nuclear Safety and Advanced Nuclear Energy Technology, Ministry of Industry and Information Technology, Harbin Engineering University) ;
  • Yin Fu (Key Laboratory of Nuclear Safety and Advanced Nuclear Energy Technology, Ministry of Industry and Information Technology, Harbin Engineering University)
  • Received : 2023.07.06
  • Accepted : 2024.01.22
  • Published : 2024.06.25
Download PDF
⟨ Previous Next ⟩

Abstract

As a typical active equipment, pump machinery is widely used in nuclear power plants. Although the mechanism of pump machinery in nuclear power plants is similar to that of conventional pumps, the safety and reliability requirements of nuclear pumps are higher in complex operating environments. Once there is significant performance degradation or failure, it may cause huge security risks and economic losses. There are many pumps mechanical parameters, and it is very important to explore the correlation between multi-dimensional variables and condition. Therefore, a condition monitoring model based on Deep Denoising Autoencoder (DDAE) is constructed in this paper. This model not only ensures low false positive rate, but also realizes early abnormal monitoring and location. In order to alleviate the influence of parameter time-varying effect on the model in long-term monitoring, this paper combined equidistant sampling strategy and DDAE model to enhance the monitoring efficiency. By using the simulation data of reactor coolant pump and the actual centrifugal pump data, the monitoring and positioning capabilities of the proposed scheme under normal and abnormal conditions were verified. This paper has important reference significance for improving the intelligent operation and maintenance efficiency of nuclear power plants.

Keywords

Acknowledgement

This work is financially supported by Leading Scientific Research Project of China National Nuclear Corporation (G4821020), and the National Natural Science Foundation of China (U21B2083).

References

  1. S. Zhu, H. Xia, B. Peng, et al., Condition monitoring model for sensors of reactor coolant pump based on PCA, Nucl. Power Eng. 41 (2020) 170-176.
  2. Y. Yu, M. Peng, H. Wang, et al., Improved PCA model for multiple fault detection, isolation and reconstruction of sensors in nuclear power plant, Ann. Nucl. Energy 148 (2020) 107662.
  3. W. Li, M. Peng, Q. Wang, Fault detectability analysis in PCA method during condition monitoring of sensors in a nuclear power plant, Ann. Nucl. Energy 119 (2018) 342-351.
  4. H. Wang, Research on Health Condition Monitoring Method of Wind Turbine Based on Data-Driven (Doctoral Dissertation), Yanshan University, 2020.
  5. L. Eren, T. Ince, S. Kiranyaz, A generic intelligent bearing fault diagnosis system using compact adaptive 1D CNN classifier, Journal of Signal Processing Systems 91 (2019) 179-189.
  6. X. Wu, Z. Peng, J. Ren, et al., Rub-impact fault diagnosis of rotating machinery based on 1-D convolutional neural networks, IEEE Sensor. J. 20 (2019) 8349-8363.
  7. X. Guo, L. Chen, C. Shen, Hierarchical adaptive deep convolution neural network and its application to bearing fault diagnosis, Measurement 93 (2016) 490-502.
  8. Y. Han, B. Tang, L. Deng, An enhanced convolutional neural network with enlarged receptive fields for fault diagnosis of planetary gearboxes, Comput. Ind. 107 (2019) 50-58.
  9. X. Wu, Y. Zhang, C. Cheng, et al., A hybrid classification autoencoder for semi-supervised fault diagnosis in rotating machinery, Mech. Syst. Signal Process. 149 (2021) 107327.
  10. X. Li, J. Li, Y. Qu, et al., Semi-supervised gear fault diagnosis using raw vibration signal based on deep learning, Chin. J. Aeronaut. 33 (2020) 418-426.
  11. H. Shao, H. Jiang, H. Zhao, et al., A novel deep autoencoder feature learning method for rotating machinery fault diagnosis, Mech. Syst. Signal Process. 95 (2017) 187-204.
  12. G. Kang, S. Gao, L. Yu, et al., Deep architecture for high-speed railway insulator surface defect detection: denoising autoencoder with multitask learning, IEEE Trans. Instrum. Meas. 68 (2018) 2679-2690.
  13. Y. Yu, M. Peng, H. Wang, et al., A continuous learning monitoring strategy for multi-condition of nuclear power plant, Ann. Nucl. Energy 164 (2021) 108544.
  14. P. Fu, X. Hu, Anomaly detection algorithm based on the local distance of density-based sampling data, J. Software 28 (2017) 2625-2639.
  15. F. Yuan, L. Zhang, J. Shi, et al., Theories and applications of auto-encoder neural networks: a literature survey, Chin. J. Comput. 42 (2019) 203-230.
  16. J. Tong, J. Luo, J. Zheng, Rolling bearing fault diagnosis method based on enhanced deep autoencoder network, China Mech. Eng. 32 (2021) 2617-2624.
  17. J. Lai, X. Wang, Q. Xiang, et al., Review on autoencoder and its application, J. Commun. 42 (2021) 218-230.
  18. J. Chen, J. Li, W. Chen, et al., A method for detecting anomaly conditions of wind turbines using stacked denoising autoencoders with sliding window and multiple noise ratios, Trans. China Electrotech. Soc. 35 (2020) 346-358.
  19. W. Yu, C. Zhao, Robust monitoring and fault isolation of nonlinear industrial processes using denoising autoencoder and elastic net, IEEE Trans. Control Syst. Technol. 28 (2019) 1083-1091.
  20. Y. Xiong, R. Zuo, Robust feature extraction for geochemical anomaly recognition using a stacked convolutional denoising autoencoder, Math. Geosci. 54 (2022) 623-644.
  21. N. Renstrom, P. Bangalore, E. Highcock, System-wide anomaly detection in wind turbines using deep autoencoders, Renew. Energy 157 (2020) 647-659.
  22. Y. Zhang, K. Xing, R. Bai, et al., An enhanced convolutional neural network for bearing fault diagnosis based on time-frequency image, Measurement 157 (2020) 107667.
  23. J. Yu, C. Zhang, Manifold regularized stacked autoencoders-based feature learning for fault detection in industrial processes, J. Process Control 92 (2020) 119-136.
  24. T. Wu, T. Liu, H. Shi, et al., Research on condition monitoring technology for nuclear power plant equipment based on kernel principal component analysis, Nucl. Power Eng. 41 (2020) 132-137.
  25. Q. Jiang, X. Yan, B. Huang, Performance-driven distributed PCA process monitoring based on fault-relevant variable selection and Bayesian inference, IEEE Trans. Ind. Electron. 63 (2015) 377-386.
  26. X. Ai, Research on Intelligent Fault Diagnostic Method for Primary Loop System of Nuclear Power Plant (Masteral Dissertation), Harbin Engineering University, 2020.
  27. X. Liang, F. Duan, I. Bennett, et al., A sparse autoencoder-based unsupervised scheme for pump fault detection and isolation, Appl. Sci. 10 (2020) 6789.
  28. Y. Fang, S. Yan, J. Li, et al., Multi-objective optimization of sum of squares double exponentially weighted moving average chart and its application in output sensor fault detection, Control Decis. 37 (2022) 1656-1664.
  29. S. Zhu, H. Xia, M. Annor-Nyarko, et al., A robust strategy for sensor fault detection in nuclear power plants based on principal component analysis, Ann. Nucl. Energy 164 (2021) 108621.
  30. G. Liu, S. Yang, G. Wang, et al., A decision-making method for machinery abnormalities based on neural network prediction and Bayesian hypothesis testing, Electronics 10 (2021) 1610.