본문 바로가기
KERD
논문KCI 등재

Imbalanced data fault diagnosis method for nuclear power plants based on convolutional variational autoencoding Wasserstein generative adversarial network and random forest

Sun Xiang|Guo Jun|Wang Yulong|Liu Shiqiao|Du Baigang
한국원자력학회 (Korean Nuclear Society)|2024.12|Nuclear Engineering and Technology|제56권 제12호|pp. 5055-5067|DOI 10.1016/j.net.2024.07.015

1

조회

0

다운로드

1

인용

0

참고문헌

키워드

Feature selectionRandom forestNuclear power plantsImbalanced data fault diagnosisConvolutional variational autoencodinggradient-penalty Wasserstein generativeadversarial network
주제분류원자력공학

초록

Data-driven fault diagnosis techniques are significant for the stable operation of nuclear power plants (NPPs). However, in practical applications, the fault diagnosis of NPPs usually faces imbalance data problems with small fault samples and much redundant data which results in low model training efficiency and poor generalization performance. Thus, this paper proposes a convolutional variational autoencoding gradient-penalty Wasserstein generative adversarial network with random forest (CVGR) to reduce the impact of imbalanced samples on fault diagnosis. Firstly, a feature selection method based on the random forest is used to identify the most relevant measurements and reduce the impact of redundant data on fault diagnosis. Then, variational autoencoding is introduced into gradient-penalty Wasserstein generative adversarial to effectively extract original sample features and generate high-quality samples with high rationality and diversity. In addition, the convolutional neural network is used to extract the features of mixed samples to realize intelligent fault diagnosis. Finally, several experiments based on the Fuqing Unit 2 full-scope simulator under different operating conditions are used to validate the performance of the CVGR in data enhancement and intelligent fault diagnosis. The results show that the proposed method can effectively mitigate the imbalance data problem, which gives insights into intelligent fault diagnosis of NPPs.

Abstract

Data-driven fault diagnosis techniques are significant for the stable operation of nuclear power plants (NPPs). However, in practical applications, the fault diagnosis of NPPs usually faces imbalance data problems with small fault samples and much redundant data which results in low model training efficiency and poor generalization performance. Thus, this paper proposes a convolutional variational autoencoding gradient-penalty Wasserstein generative adversarial network with random forest (CVGR) to reduce the impact of imbalanced samples on fault diagnosis. Firstly, a feature selection method based on the random forest is used to identify the most relevant measurements and reduce the impact of redundant data on fault diagnosis. Then, variational autoencoding is introduced into gradient-penalty Wasserstein generative adversarial to effectively extract original sample features and generate high-quality samples with high rationality and diversity. In addition, the convolutional neural network is used to extract the features of mixed samples to realize intelligent fault diagnosis. Finally, several experiments based on the Fuqing Unit 2 full-scope simulator under different operating conditions are used to validate the performance of the CVGR in data enhancement and intelligent fault diagnosis. The results show that the proposed method can effectively mitigate the imbalance data problem, which gives insights into intelligent fault diagnosis of NPPs.

참고문헌 (38)

  1. A. Azam, "Analyzing the effect of natural gas, nuclear energy and renewable energy on GDP and carbon emissions: a multivariate panel data analysis", Energy, 219, pp.119592~ (2021)[DOI]
  2. L. Yong-Kuo, "Research and design of distributed fault diagnosis system in nuclear power plant", Prog. Nucl. Energy, 68, pp.97~110 (2013)[DOI]
  3. T. Lind, "Phase 2 – results of severe accident analyses for unit 3", Nucl. Eng. Des, 376, pp.111138~ (2021)[DOI]
  4. B. -S. Peng, "Research on intelligent fault diagnosis method for nuclear power plant based on correlation analysis and deep belief network", Prog. Nucl. Energy, 108, pp.419~427 (2018)[DOI]
  5. J. Park, "Aging detection of plant control system components using recurrent neural network", Prog. Nucl. Energy, 142, pp.104005~ (2021)[DOI]
  6. W. Yin, "A fault diagnosis of nuclear power plant rotating machinery based on multi-sensor and deep residual neural network", Ann. Nucl. Energy, 185, pp.109700~ (2023)[DOI]
  7. J. Choi, "RNN-based integrated system for real-time sensor fault detection and fault-informed accident diagnosis in nuclear power plant accidents", Nucl. Eng. Technol, 55, pp.814~826 (2023)[DOI]
  8. G. -J. Qi, "Small data challenges in big data era : a survey of recent progress on unsupervised and semi-supervised methods", IEEE Trans. Pattern Anal. Mach. Intell, 44, pp.2168~2187 (2022)[DOI]
  9. I. Goodfellow, "Generative adversarial networks", Commun. ACM, 63, pp.139~144 (2020)[DOI]
  10. S. Shao, "Generative adversarial networks for data augmentation in machine fault diagnosis", Comput. Ind, 106, pp.85~93 (2019)[DOI]
  11. P. Liang, "A deep capsule neural network with data augmentation generative adversarial networks for single and simultaneous fault diagnosis of wind turbine gearbox", ISA Trans, 135, pp.462~475 (2023)[DOI]
  12. Y. Dai, "An intelligent fault diagnosis method for imbalanced nuclear power plant data based on generative adversarial networks", J. Electr. Eng. Technol, 18, pp.3237~3252 (2023)[DOI]
  13. Z. Wang, "Imbalanced sample fault diagnosis method for rotating machinery in nuclear power plants based on deep convolutional conditional generative adversarial network", Nucl. Eng. Technol, 55, pp.2096~2106 (2023)[DOI]
  14. G. Qian, "Fault diagnosis based on conditional generative adversarial networks in nuclear power plants", Ann. Nucl. Energy, 176, pp.109267~ (2022)[DOI]
  15. K. Zhou, "Deep convolutional generative adversarial network with semi-supervised learning enabled physics elucidation for extended gear fault diagnosis under data limitations", Mech. Syst. Signal Process, 185, pp.109772~ (2023)[DOI]
  16. Z. Shang, "A novel small samples fault diagnosis method based on the self-attention wasserstein generative adversarial network", Neural Process. Lett, 55, pp.6377~6407 (2023)[DOI]
  17. M. Arjovsky, "Wasserstein generative adversarial networks", Proceedings of the 34th International Conference on Machine Learning (2017)
  18. "Auto-encoding variational bayes, CoRR abs/1312.6114" (2013)[URL]
  19. X. Zhao, "Normalized Conditional Variational AutoEncoder with adaptive Focal loss for imbalanced fault diagnosis of Bearing-Rotor system", Mech. Syst. Signal Process, 170 (2022)[DOI]
  20. Y. Zhu, "A hybrid Artificial Immune optimization for high-dimensional feature selection", Knowl. Base Syst, 260, pp.110111~ (2023)[DOI]
  21. B. -S. Yang, "Random forests classifier for machine fault diagnosis", J. Mech. Sci. Technol, 22, pp.1716~1725 (2008)[DOI]
  22. L. Cehovin, "Empirical evaluation of feature selection methods in classification", Adv. Eng. Inf, 14, pp.265~281 (2010)
  23. S. Xu, "A collaborative filtering framework based on variational autoencoders and generative adversarial networks", 2020 International Conference on Computer Information and Big Data Applications (CIBDA) (2020)
  24. S. Liu, "Machine fault diagnosis with small sample based on variational information constrained generative adversarial network", Adv. Eng. Inf, 54, pp.18~ (2022)[DOI]
  26. I. Gulrajani, "Improved training of wasserstein GANs", Proceedings of the 31st International Conference on Neural Information Processing Systems (2017)
  27. A.B.L. Larsen, "Autoencoding beyond pixels using a learned similarity metric", Proceedings of the 33rd International Conference on International Conference on Machine Learning, 48 (2016)
  28. X.X. Wang, "Research on fault pattern analysis of marine diesel engine based on random forest algorithm", 2017 4th International Conference on Transportation Information and Safety (ICTIS) (2017)
  29. D. Ruan, "Improvement of generative adversarial network and its application in bearing fault diagnosis : a review", Lubricants, 11, pp.74~ (2023)[DOI]
  30. V. D. M. Laurens, "Visualizing Data using t-SNE", J. Mach. Learn, 9, pp.2579~2605 (2008)
  31. Q. Tong, "A novel method for fault diagnosis of bearings with small and imbalanced data based on generative adversarial networks", Appl. Sci, 12, pp.7346~ (2022)[DOI]
  32. D. Ruan, "Collaborative optimization of CNN and GAN for bearing fault diagnosis under unbalanced datasets", Lubricants, 9, pp.105~ (2021)[DOI]
  33. J. Wang, "Rolling bearing fault diagnosis method based on SSAE and softmax classifier with improved K-fold cross-validation", Meas. Sci. Technol, 33, pp.105110~ (2022)[DOI]
  34. Z. Wang, "An intelligent diagnosis scheme based on generative adversarial learning deep neural networks and its application to planetary gearbox fault pattern recognition", Neurocomputing, 310, pp.213~222 (2018)[DOI]
  35. S. Liu, "Rolling bearing fault diagnosis using variational autoencoding generative adversarial networks with deep regret analysis", Measurement, 168, pp.108371~ (2021)[DOI]
  36. H. Zhu, "Imbalance domain adaptation network with adversarial learning for fault diagnosis of rolling bearing", Signal Image Video Process, 16, pp.2249~2257 (2022)[DOI]
  37. J. Li, "Transfer learning with limited labeled data for fault diagnosis in nuclear power plants", Nucl. Eng. Des, 390, pp.111690~ (2022)[DOI]
  38. J. Li, "Research on robustness of five typical data-driven fault diagnosis models for nuclear power plants", Ann. Nucl. Energy, 165, pp.108639~ (2022)[DOI]

관련 논문AI추천

Imbalanced sample fault diagnosis method for rotating machinery in nuclear power plants based on deep convolutional conditional generative adversarial networkWang Zhichao, Xia Hong, Yang Bo, Yin Wenzhe, Zhang Jiyu한국원자력학회 · Nuclear Engineering and Technology2023 · 제55권 제6호Fault diagnosis of nuclear power plant sliding bearing-rotor systems using deep convolutional generative adversarial networksChen Feiyu, Huang Guobing, Li Qi, Wang Xiaojing, Xiong Xin, Yuan Weimin, Zhang Weiwei한국원자력학회 · Nuclear Engineering and Technology2024 · 제56권 제8호Research on unsupervised condition monitoring method of pump-type machinery in nuclear power plantFu Yin, Wang Zhichao, Xia Hong, Zhang Jiyu, Zhu Yihu한국원자력학회 · Nuclear Engineering and Technology2024 · 제56권 제6호Approach to diagnosing multiple abnormal events with single-event training data구서룡, 신지현, 이승준, 조승규한국원자력학회 · Nuclear Engineering and Technology2024 · 제56권 제2호Using artificial intelligence to detect human errors in nuclear power plants: A case in operation and maintenanceAgarwal Vivek, Boring Ronald L., Coble Jamie Baalis, Gursel Ezgi, Khojandi Anahita, Madadi Mahboubeh, Reddy Bhavya, Yadav Vaibhav한국원자력학회 · Nuclear Engineering and Technology2023 · 제55권 제2호Robust transformer-based anomaly detection for nuclear power data using maximum correntropy criterionHe Junjie, Yang Senquan, Yi Shuang, Zheng Sheng, Zhou Guangrong한국원자력학회 · Nuclear Engineering and Technology2024 · 제56권 제4호

이 간행물의 다른 논문 (49건)

Loss of power accident analysis for the HCCR blanket김석권, 안무영, 진형곤, 문성보pp. 4947-4950Effects of electrode configuration on the current density distribution of the electrolytic reducer허진목, 류재수, 이상권pp. 4951-4958Study on quantitative interpretation of uranium spectral gamma-ray logging based on machine learning algorithmWang Renbo, Huang Haolong, Fu Chunqing, Qiu Jun, Ye Yujin, Zhang Yan, Tang Binpp. 4959-4965Assessment of environmental hazard impacts in building materials (Marble), Gabal El-Galala El-Bahariya, Northeastern Desert, EgyptAbd El Rahman R.M., Hanfi M.Y., Alqahtani Mohammad S.pp. 4966-4974Confirmation bias, information selection, and belief reinforcement about the safety/risk of nuclear spent fuel storage facilities최영록, Kim Woo J., 이대윤pp. 4975-4982
원문 보기