Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Imbalanced sample fault diagnosis method for rotating machinery in nuclear power plants based on deep convolutional conditional generative adversarial network

  • Zhichao Wang (Fundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University) ;
  • Hong Xia (Fundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University) ;
  • Jiyu Zhang (Fundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University) ;
  • Bo Yang (Fundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University) ;
  • Wenzhe Yin (Fundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University)
  • Received : 2022.04.21
  • Accepted : 2023.02.27
  • Published : 2023.06.25
Download PDF
⟨ Previous Next ⟩

Abstract

Rotating machinery is widely applied in important equipment of nuclear power plants (NPPs), such as pumps and valves. The research on intelligent fault diagnosis of rotating machinery is crucial to ensure the safe operation of related equipment in NPPs. However, in practical applications, data-driven fault diagnosis faces the problem of small and imbalanced samples, resulting in low model training efficiency and poor generalization performance. Therefore, a deep convolutional conditional generative adversarial network (DCCGAN) is constructed to mitigate the impact of imbalanced samples on fault diagnosis. First, a conditional generative adversarial model is designed based on convolutional neural networks to effectively augment imbalanced samples. The original sample features can be effectively extracted by the model based on conditional generative adversarial strategy and appropriate number of filters. In addition, high-quality generated samples are ensured through the visualization of model training process and samples features. Then, a deep convolutional neural network (DCNN) is designed to extract features of mixed samples and implement intelligent fault diagnosis. Finally, based on multi-fault experimental data of motor and bearing, the performance of DCCGAN model for data augmentation and intelligent fault diagnosis is verified. The proposed method effectively alleviates the problem of imbalanced samples, and shows its application value in intelligent fault diagnosis of actual NPPs.

Keywords

Acknowledgement

This work is financially supported by National Defense Science and Technology Industry Nuclear Power Technology Innovation Center Fund (HDLCXZX-2021-ZH-019), and the Fundamental Research Funds for the Central Universities (3072021GIP1503), and the National Natural Science Foundation of China (U21B2083).

References

  1. G.S. Qian, J.Q. Liu, Development of deep reinforcement learning-based fault diagnosis method for rotating machinery in nuclear power plants, Prog. Nucl. Energy 152 (2022), 104401.
  2. S. Singh, N. Kumar, Detection of bearing faults in mechanical systems using stator current monitoring, IEEE Trans. Ind. Inf. 13 (2017) 1341-1349. https://doi.org/10.1109/TII.2016.2641470
  3. C.S. Goo, S.M. Jang, Y.S. Park, Condition monitoring of squirrel cage induction motor through torque evaluation, in: 2012 IEEE International Conference on Power System Technology (POWERCON), Auckland, New Zealand, 2012. Oct 30-Nov 02.
  4. L.L. Hao, J.L. Chen, J.H. Li, et al., Diagnosis of rotor winding short-circuit fault in multi-phase annular brushless exciter through stator field current harmonics, IEEE Trans. Energy Convers. 36 (2021) 1808-1817. https://doi.org/10.1109/TEC.2021.3058279
  5. A. Glowacz, W. Glowacz, J. Kozik, et al., Detection of deterioration of three-phase induction motor using vibration signals, Meas. Sci. Rev. 19 (2019) 241-249. https://doi.org/10.2478/msr-2019-0031
  6. S. Pan, T. Han, A.C.C. Tan, et al., Fault diagnosis system of induction motors based on multiscale entropy and support vector machine with mutual information algorithm, Shock Vib. 2016 (2016), 5836717.
  7. K. Li, L. Su, J.J. Wu, et al., A rolling bearing fault diagnosis method based on variational mode decomposition and an improved kernel extreme learning machine, Applied Sciences-Basel 7 (2017) 1004.
  8. M.Z. Ali, M.N.S.K. Shabbir, X.D. Liang, et al., Machine learning-based fault diagnosis for single-and multi-faults in induction motors using measured stator currents and vibration signals, IEEE Trans. Ind. Appl. 55 (2019) 2378-2391. https://doi.org/10.1109/TIA.2019.2895797
  9. S.Y. Shao, R.Q. Yan, Y.D. Lu, et al., DCNN-based multi-signal induction motor fault diagnosis, IEEE Trans. Instrum. Meas. 69 (2020) 2658-2669. https://doi.org/10.1109/TIM.2019.2925247
  10. D.Y. Xiao, Y.X. Huang, X.D. Zhang, et al., Fault diagnosis of asynchronous motors based on LSTM neural network, in: 2018 Prognostics and System Health Management Conference, 2018. Chongqing, China, Oct 26-28.
  11. J. Zhu, T.Z. Hu, B. Jiang, et al., Intelligent bearing fault diagnosis using PCA-DBN framework, Neural Comput. Appl. 32 (2020) 10773-10781. https://doi.org/10.1007/s00521-019-04612-z
  12. 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
  13. A. Ayodeji, Y.K. Liu, N. Chao, et al., A new perspective towards the development of robust data-driven intrusion detection for industrial control systems, Nucl. Eng. Technol. 52 (2020) 2687-2698. https://doi.org/10.1016/j.net.2020.05.012
  14. I. Martin-Diaz, D. Morinigo-Sotelo, O. Duque-Perez, et al., Early fault detection in induction motors using AdaBoost with imbalanced small data and optimized sampling, IEEE Trans. Ind. Appl. 53 (2017) 3066-3075. https://doi.org/10.1109/TIA.2016.2618756
  15. A. Almounajjed, A.K. Sahoo, M.K. Kumar, Condition monitoring and fault detection of induction motor based on wavelet denoising with ensemble learning, Electr. Eng. 104 (2022) 2859-2877. https://doi.org/10.1007/s00202-022-01523-6
  16. H. Ljubic, G. Martinovic, T. Volaric, Augmenting data with generative adversarial networks: an overview, Intell. Data Anal. 26 (2022) 361-378. https://doi.org/10.3233/IDA-215735
  17. W.T. Mao, Y.M. Liu, L. Ding, et al., Imbalanced fault diagnosis of rolling bearing based on generative adversarial network: a comparative study, IEEE Access 7 (2019) 9515-9530. https://doi.org/10.1109/ACCESS.2018.2890693
  18. Y.R. Wang, G.D. Sun, Q. Jin, Imbalanced sample fault diagnosis of rotating machinery using conditional variational auto-encoder generative adversarial network, Appl. Soft Comput. 92 (2020), 106333.
  19. Y. Xu, Z.X. Li, S.Q. Wang, et al., A hybrid deep-learning model for fault diagnosis of rolling bearings, Measurement 169 (2021), 108502.
  20. W. Zhou, D.P. Ming, X.W. Lv, et al., SO-CNN based urban functional zone fine division with VHR remote sensing image, Rem. Sens. Environ. 236 (2020), 111458.
  21. R. Yang, Z.R. Pan, X.X. Jia, et al., A novel CNN-based detector for ship detection based on rotatable bounding box in SAR images, IEEE J. Sel. Top. Appl. Earth Obs. Rem. Sens. 14 (2021) 1938-1958. https://doi.org/10.1109/JSTARS.2021.3049851
  22. T. Setthanun, J. Saichon, P. Anantachai, et al., ConvXGB: a new deep learning model for classification problems based on CNN and XGBoost, Nucl. Eng. Technol. 53 (2021) 522-531. https://doi.org/10.1016/j.net.2020.04.008
  23. I.J. Goodfellow, J. Pouget-Abadie, M. Mirza, et al., Generative adversarial nets, in: 28th Conference on Neural Information Processing Systems (NIPS), 2014. Montreal, Canada, Dec 08-13.
  24. X. Gao, F. Deng, X.H. Yue, Data augmentation in fault diagnosis based on the Wasserstein generative adversarial network with gradient penalty, Neurocomputing 396 (2020) 487-494. https://doi.org/10.1016/j.neucom.2018.10.109
  25. M. Mirza, S. Osindero, Conditional Generative Adversarial Nets, 2014 arXiv preprint arXiv: 1411.1784.
  26. Z.C. Wu, P.C. Jiang, C. Ding, et al., Intelligent fault diagnosis of rotating machinery based on one-dimensional convolutional neural network, Comput. Ind. 108 (2019) 53-61. https://doi.org/10.1016/j.compind.2018.12.001
  27. X.P. Zhong, H. Ban, Pre-trained network-based transfer learning: a small sample machine learning approach to nuclear power plant classification problem, Ann. Nucl. Energy 175 (2022), 109201.
  28. X.P. Zhong, H. Ban, Crack fault diagnosis of rotating machine in nuclear power plant based on ensemble learning, Ann. Nucl. Energy 168 (2022), 108909.
  29. S. Asante-Okyere, C.B. Shen, Y.Y. Ziggah, et al., Principal component analysis (PCA) based hybrid models for the accurate estimation of reservoir water saturation, Comput. Geosci. 145 (2020), 104555.