Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Cavitation state identification of centrifugal pump based on CEEMD-DRSN

  • Cui Dai (School of Energy and Power Engineering, Jiangsu University) ;
  • Siyuan Hu (Research Center of Fluid Machinery Engineering and Technology, Jiangsu University) ;
  • Yuhang Zhang (Research Center of Fluid Machinery Engineering and Technology, Jiangsu University) ;
  • Zeyu Chen (Research Center of Fluid Machinery Engineering and Technology, Jiangsu University) ;
  • Liang Dong (Research Center of Fluid Machinery Engineering and Technology, Jiangsu University)
  • Received : 2022.09.07
  • Accepted : 2023.01.12
  • Published : 2023.04.25
Download PDF
⟨ Previous Next ⟩

Abstract

Centrifugal pumps are a crucial part of nuclear power plants, and their dependable and safe operation is crucial to the security of the entire facility. Cavitation will cause the centrifugal pump to violently vibration with the large number of vacuoles generated, which not only affect the hydraulic performance of the centrifugal pump but also cause structural damage to the impeller, seriously affecting the operational safety of nuclear power plants. A closed cavitation test bench of a centrifugal pump is constructed, and a method for precisely identifying the cavitation state is proposed based on Complementary Ensemble Empirical Mode Decomposition (CEEMD) and Deep Residual Shrinkage Network (DRSN). First, we compared the cavitation sensitivity of pressure fluctuation, vibration, and liquid-borne noise and decomposed the liquid-borne noise by CEEMD to capture cavitation characteristics. The decomposition results are sent into a 12-layer deep residual shrinkage network (DRSN) for cavitation identification training. The results demonstrate that the liquid-borne noise signal is the most cavitation-sensitive signal, and the accuracy of CEEMD-DRSN to identify cavitation at different stages of centrifugal pumps arrives at 94.61%

Keywords

Acknowledgement

The authors would like to thank the financial support from National Natural Science Foundation of China (No. 52279087, 51879122), Zhenjiang key research and development plan (GY2017001, GY2018025),the Open Research Subject of Key Laboratory of Fluid and Power Machinery, Ministry of Education, Xi-hua University (szjj2017094, szjj2016068), Jiangsu University Young Talent training Program-Outstanding Young backbone Teacher, Program Development of Jiangsu Higher Education Institutions (PAPD), and Jiangsu top six talent summit project (GDZB-017).

References

  1. S. Li, H. Wang, L. Song, P. Wang, L. Cui, T. Lin, An adaptive data fusion strategy for fault diagnosis based on the convolutional neural network, Measurement 165 (2020) 108-222, https://doi.org/10.1016/j.measurement.2020.108122.
  2. C. He, G. Zhang, Research progress of cavitation formation mechanism and technology application, J. Qinghai Normal Univ. (Nat. Sci) 31 (3) (2015) 52-55. https://10.16229/j.cnki.issn1001-7542.2015.03.010.
  3. C. Qun, J. Tao, W. Xiaoliang, Y. Wang, L. Meng, C. liang Liu, Cavitation intensity recognition for high-speed axial piston pumps using 1-d convolutional neural networks with multichannel inputs of vibration signals, Alex. Eng. J. 59 (6) (2020) 4463-4473, https://doi.org/10.1016/j.aej.2020.07.052.
  4. D. Hoang, H. Kang, Rolling element bearing fault diagnosis using convolutional neural network and vibration image, Cognit. Syst. Res. 53 (6) (2019) 42-50, https://doi.org/10.1016/j.cogsys.2018.03.002.
  5. J. Yeh, J.S. Shieh, N.E. Huang, Complementary ensemble empirical mode decomposition: a novel noise enhanced data analysis method, Adv. Data Sci. Adapt. Anal. 2 (2010) 135-156, https://doi.org/10.1142/S1793536910000422.
  6. W. Zhang, G. Tong, L. Li, W. Zhao, X.Z. Hu, Kl-CEEMD based method for identifying false components of rotor fault signals of high-position steam turbine units, Turbine Technol. 64 (2) (2022) 115-119, https://doi.org/10.3969/j.issn.1001-5884.2022.02.011.
  7. S. Heo, J.H. Lee, Fault detection and classification using artificial neural networks, IFAC-PapersOnLine 51 (18) (2018) 470-475, https://doi.org/10.1016/j.ifacol.2018.09.380.
  8. K. Fukushima, S. Miyake, Neocognitron: a self-organizing neural network model for a mechanism of visual pattern recognition, in: S.i. Amari, M.A. Arbib (Eds.), Competition and Cooperation in Neural Nets, Springer Berlin Heidelberg, Berlin, Heidelberg, 1982.
  9. T.J. Li, Y.C. Zhao, X. Li, C.S. Zhu, J.R. Ning, Fault diagnosis of water pump based on probabilistic neural network, Adv. Mater. Res. 338 (2011) 421-424. https://doi.org/10.4028/www.scientific.net/amr.338.421.
  10. Lee Sin-Young, Acoustic diagnosis of a pump by using neural network, J. Mech. Sci. Technol. 20 (2006) 2079-2086, https://doi.org/10.1007/BF02916324.
  11. G. Mousmoulisa, C. Yiakopoulosb, G. Aggidisc, I. Antoniadisb, I. Anagnostopoulos, Application of Spectral Kurtosis on vibration signals for the detection of cavitation in centrifugal pumps, Appl. Acoust. 182 (November 2021), https://doi.org/10.1016/j.apacoust.2021.108289.
  12. Hajnayeb Ali, Cavitation analysis in centrifugal pumps based on vibration bispectrum and transfer learning, Shock Vib. (2021), https://doi.org/10.1155/2021/6988949.
  13. R. Azizi, A. Hajnayeb, A. Ghanbarzadeh, M. Changizian, Cavitation severity detection in centrifugal pumps, Int. Congress. Tech. Diagnostic. 10 (2018) 47-55, https://doi.org/10.1007/978-3-319-62042-8_4.
  14. T. Ye, Q. Si, C. Shen, S. Yang, S. Yuan, Monitoring of primary cavitation of centrifugal pump based on support vector machine, J. Drainage. Irrigation. Machinery Eng. 39 (2021).
  15. K. Wu, Y. Xing, N. Chu, P. Wu, A carrier wave extraction method for cavitation characterization based on time synchronous average and time-frequency analysis, J. Sound Vib. 489 (2020), 115682, https://doi.org/10.1016/j.jsv.2020.115682.
  16. Q. Chao, J. Tao, X. Wei, C. Liu, Measurement Science and Technology PAPER Identification of cavitation intensity for high-speed aviation hydraulic pumps using 2D convolutional neural networks with an input of RGB-based vibration data, Meas. Sci. Technol. (2020), https://doi.org/10.1088/1361-6501/ab8d5a.
  17. L. Dong, K. Wu, J. Zhu, C. Dai, Cavitation detection in centrifugal pump based on interior flow-borne noise using WPD-PCA-RBF, Shock Vib. (2019) 1-12, https://doi.org/10.1155/2019/8768043.
  18. X. Liang, Y. Luo, F. Deng, Y. Li, Investigation on vibration signal characteristics in a centrifugal pump using EMD-LS-MFDFA, Processes 10 (2022) 1169, https://doi.org/10.3390/pr10061169.
  19. Ruijia Cao, Jianping Yuan, et al., Numerical method to predict vibration characteristics induced by cavitation in centrifugal pumps, Meas. Sci. Technol. 32 (11) (2021), https://doi.org/10.1088/1361-6501/ac1181.
  20. A. Hajnayeb, R. Azizi, A. Ghanbarzadeh, M. Changizian, Vibration-based Cavitation Detection in Centrifugal Pumps, Diagnostyka, 2017.
  21. Z. Wu, N.E. Huang, Ensemble empirical mode decomposition: a noise-assisted data analysis method[J], Adv. Adapt. Data Anal. 1 (1) (2009) 1-41. https://doi.org/10.1142/S1793536909000047
  22. M. Liu, L. Tan, S. Cao, Influence of geometry of inlet guide vanes on pressure fluctuations of a centrifugal pump, May 2, 2018, ASME. J. Fluids Eng. September 140 (9) (2018), 091204, https://doi.org/10.1115/1.4039714.
  23. Lu, Y. Tan L., Han, Y. Liu, M., Cavitation-vibration correlation of a mixed flow pump under steady state and fast start-up conditions by experiment, Ocean Eng., Volume 251, 2022,. https://doi.org/10.1016/j.oceaneng.2022.111158.
  24. M. Liu, L. Tan, S. Cao, Cavitation-vortex-turbulence interaction and one-dimensional model prediction of pressure for hydrofoil ALE15 by large eddy simulation, ASME. J. Fluids Eng, February 141 (2) (2019), 021103, https://doi.org/10.1115/1.4040502.
  25. W. Sun, L. Tan, Cavitation-vortex-pressure fluctuation interaction in a centrifugal pump using bubble rotation modified cavitation model under partial load, ASME. J. Fluids Eng.,May 142 (5) (2020), 051206, https://doi.org/10.1115/1.4045615.
  26. X. Ding, J. Xu, W. Teng, et al., Fault feature extraction of a wind turbine gearbox using adaptive parameterless empirical wavelet transform[J], J. Vib. Shock 39 (8) (2020) 99-105.
  27. Quan Zhou, Yi-bing Li, Yu Tian, et al., A novel method based on nonlinear auto-regression neural network and convolutional neural network for imbalanced fault diagnosis of rotating machinery[J], Measurement 161 (2020) 107-180. https://doi.org/10.1016/j.measurement.2020.107880
  28. L. Dong, Y. Zhao, C. Dai, Detection of inception cavitation in centrifugal pump by fluid-borne noise diagnostic, Shock Vib. 2019 (2019), https://doi.org/10.1155/2019/9641478.
  29. L. Dong, Y. Zhao, C. Dai, Study on unstable characteristics of centrifugal pump under dierent cavitation stages, J. Therm. Sci. 28 (2019) 608-620, https://doi.org/10.1007/s11630-019-1136-2.
  30. J. Lu, S. Yuan, P. Siva, J. Yuan, The characteristics investigation under the unsteady cavitation condition in a centrifugal pump, J. Mech. Sci. Technol. 31 (2017) 1213-1222, https://doi.org/10.1007/s12206-017-0220-3.
  31. J. Lu, S. Yuan, X. Li, Q. Si, Y. Luo, Research on the characteristics of quasi-steady cavitation in a centrifugal pump, IOP Conf. Ser. Mater. Sci. Eng. 72 (2015), 032017, https://doi.org/10.1088/1757-899X/72/3/032017.
  32. L. Dong, Y. Zhao, J. Xiao, H. Liu, Change mechanism of vibration and noise characteristics before and after cavitation in hydraulic retarder, Trans. Chin. Soc. Agric. Eng. 33 (2017) 56-62, https://doi.org/10.11975/j.issn.1002-6819.2017.14.008. 
  33. M.F. Hamilton, D.E. Thompson, M.L. Billet, An experimental study of travelling-bubble cavitation noise, J. Fluid Eng. 108 (2) (1986) 241-247, https://doi.org/10.1115/1.3242570.
  34. M. Zhao, S. Zhong, X. Fu, B. Tang, M. Pecht, Deep residual shrinkage networks for fault diagnosis, IEEE Trans. Ind. Inf. 16 (7) (2020) 4681-4690, https://doi.org/10.1109/TII.2019.2943898.
  35. D. Donoho, De-noising by soft-thresholding, IEEE Trans. Inf. Theor. 41 (3) (1995) 613-627, https://doi.org/10.1109/18.382009.