Nuclear Engineering and Technology

  • 제56권9호
  • /
  • Pages.3740-3749
  • /
  • 2024
  • /
  • 1738-5733(pISSN)
  • /
  • 2234-358X(eISSN)
한국원자력학회 (Korean Nuclear Society)
권호 표지
DOI QR코드

DOI QR Code

Life prediction of IGBT module for nuclear power plant rod position indicating and rod control system based on SDAE-LSTM

  • Zhi Chen (National Key Laboratory of Nuclear Reactor Technology, Nuclear Power Institute of China) ;
  • Miaoxin Dai (School of Computer Science, University of South China) ;
  • Jie Liu (School of Computer Science, University of South China) ;
  • Wei Jiang (National Key Laboratory of Nuclear Reactor Technology, Nuclear Power Institute of China) ;
  • Yuan Min (National Key Laboratory of Nuclear Reactor Technology, Nuclear Power Institute of China)
  • 투고 : 2023.04.08
  • 심사 : 2024.04.15
  • 발행 : 2024.09.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

To reduce the losses caused by aging failure of insulation gate bipolar transistor (IGBT), which is the core components of nuclear power plant rod position indicating and rod control (RPC) system. It is necessary to conduct studies on its life prediction. The selection of IGBT failure characteristic parameters in existing research relies heavily on failure principles and expert experience. Moreover, the analysis and learning of time-domain degradation data have not been fully conducted, resulting in low prediction efficiency as the monotonicity, time correlation, and poor anti-interference ability of extracted degradation features. This paper utilizes the advantages of the stacked denoising autoencoder(SDAE) network in adaptive feature extraction and denoising capabilities to perform adaptive feature extraction on IGBT time-domain degradation data; establishes a long-short-term memory (LSTM) prediction model, and optimizes the learning rate, number of nodes in the hidden layer, and number of hidden layers using the Gray Wolf Optimization (GWO) algorithm; conducts verification experiments on the IGBT accelerated aging dataset provided by NASA PCoE Research Center, and selects performance evaluation indicators to compare and analyze the prediction results of the SDAE-LSTM model, PSOLSTM model, and BP model. The results show that the SDAE-LSTM model can achieve more accurate and stable IGBT life prediction.

키워드

과제정보

This work was supported by the National Natural Science Foundation of China, grant number U2267206 ; Research Foundation of Education Bureau of Hunan Province, grant number 22C0223 and 21B0434.

참고문헌

  1. P. Duan, S. Jie, L. Liang, Y. Xu, Y. Yuan, Research on position monitoring system of rod control rod in nuclear power station, Instrumentation 30 (2023) 62-66.
  2. G. Zheng, K. Huang, H. Yu, Q. Ma, Y. Jin, Y. Tian, G. Li, Power control equipment for control rod drive mechanisms based on IGBT in nuclear power plant, Nucl. Power Eng. 35 (2014) 138-141.
  3. Z. Zhong, Y. Wang, Y. Huang, D. Xiao, P. Xia, C. Liu, Remaining useful life prediction of IGBT modules across working conditions based on ProbSparse self-attention, J. Shanghai Jiaot. Univ. 57 (2023) 1005-1015, https://doi.org/10.16183/j.cnki.jsjtu.2021.538.
  4. Y. Shi, Y. Ai, S. Chen, C. Zhang, J. Liu, A health state prediction method of traction converter IGBT based on optimized particle filter, Microelectron. Reliab. 139 (2022), https://doi.org/10.1016/j.microrel.2022.114840.
  5. Z. Ni, X. Lyu, O.P. Yadav, B.N. Singh, S. Zheng, D. Cao, Overview of real-time lifetime prediction and extension for SiC power converters, IEEE Trans. Power Electron. 35 (2020) 7765-7794, https://doi.org/10.1109/TPEL.2019.2962503.
  6. J. Zhang, J. Hu, H. You, R. Jia, X. Wang, X. Zhang, A remaining useful life prediction method of IGBT based on online status data, Microelectron. Reliab. 121 (2021), https://doi.org/10.1016/j.microrel.2021.114124.
  7. C. Li, IGBT fault prediction combining terminal characteristics and artificial intelligence neural network, Comput. Math. Methods Med. 2022 (2022), https://doi.org/10.1155/2022/7459354.
  8. D. Yu, An improved prediction model of IGBT junction temperature based on backpropagation neural network and kalman filter, Complexity 2021 (2021), https://doi.org/10.1155/2021/5542889.
  9. B. Chen, G. Lu, H. Fang, M. Zhang, Y. Dong, Prediction method of IGBT health parameters based-on degradation data and DBN algorithm, Comput. Meas. Control 25 (2017) 71-75, https://doi.org/10.16526/j.cnki.11-4762/tp.2017.05.020.
  10. Z. Liu, C. Zhu, IGBT life prediction based on Elman neural network model, Semiconductor Technology 44 (2019) 395-400, https://doi.org/10.13290/j.cnki.bdtjs.2019.05.013.
  11. B. Li, Research on Fault Prediction of IGBT Based on Terminal Characteristics, Beijing Jiaotong University, 2021, https://doi.org/10.26944/d.cnki.gbfju.2021.001513.
  12. H. Ren, Y. Yu, X. Du, J. Liu, J. Zhou, IGBT Lifetime Prediction Model Based on Optimized Long Short-Term Memory Neural Network, vol. 39, Transactions of China Electrotechnical Society, 2024, pp. 1074-1086, https://doi.org/10.19595/j.cnki.1000-6753.tces.222231.
  13. J. Zhang, Z. Xue, H. Chen, P. Sun, C. Gao, Y. Duan, CNN-BiLSTM based on attention mechanism for prediction of lGBT remaining useful life, Semiconductor Technology 49 (4) (2024) 373-379, https://doi.org/10.13290/j.cnki.bdtjs.2024.04.010.
  14. D. Astigarraga, F.M. Ibanez, A. Galarza, J.M. Echeverria, I. Unanue, P. Baraldi, E. Zio, Analysis of the results of accelerated aging tests in insulated gate bipolar transistors, IEEE Trans. Power Electron. 31 (2016) 7953-7962, https://doi.org/10.1109/TPEL.2015.2512923.
  15. M. Ma, W. Guo, M. Zhan, S. Yang, F. Li, Reconfiguration modulation strategy analysis for proactive adaptability of the monitored inverter to on-line monitoring system of IGBT modules, Energy Rep. 6 (2020) 554-565, https://doi.org/10.1016/j.egyr.2020.11.189.
  16. R. Liu, H. Li, K. Yu, R. Yao, W. Lai, J. An, X. Wang, H. Li, Analysis of package condition monitoring method of Wire-bonded lGBT devices, J. Inst. Eng. Electr. Eng. Div. 15 (2022) 71-78+82, https://doi.org/10.19768/j.cnki.dgjs.2022.15.019.
  17. A. Ismail, L. Saidi, M. Sayadi, M. Benbouzid, A new data-driven approach for power IGBT remaining useful life estimation based on feature reduction technique and neural network, Electronics (Switzerland) 9 (2020) 1-15, https://doi.org/10.3390/electronics9101571.
  18. Q. Zhang, Y. Yang, P. Zhang, A novel online chip-related aging monitoring method for IGBTs based on the leakage current, IEEE Trans. Ind. Electron. 70 (2023) 2003-2014, https://doi.org/10.1109/TIE.2022.3163516.
  19. U.M. Choi, F. Blaabjerg, S. Jorgensen, S. Munk-Nielsen, B. Rannestad, Reliability improvement of power converters by means of condition monitoring of IGBT modules, IEEE Trans. Power Electron. 32 (2017) 7990-7997, https://doi.org/10.1109/TPEL.2016.2633578.
  20. G. Sonnenfeld, K. Goebel, J. Celaya, An agile accelerated aging, characterization and scenario simulation system for gate controlled power transistors, IEEE Autotestcon (2008) 208-215, https://doi.org/10.1109/AUTEST.2008.4662613.
  21. P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio, P.-A. Manzagol, Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion, J. Mach. Learn. Res. 11 (2010) 3371-3408.
  22. X. Yan, Y. Liu, M. Jia, Health condition identification for rolling bearing using a multi-domain indicator-based optimized stacked denoising autoencoder, Struct. Health Monit. 19 (2020) 1602-1626, https://doi.org/10.1177/1475921719893594.
  23. X. Wang, J. Wu, C. Liu, H. Yang, Y. Du, W. Niu, Exploring LSTM based recurrent neural network for failure time series prediction, J. Beijing Univ. Aeronaut. Astronaut. 44 (2018) 772-784, https://doi.org/10.13700/j.bh.1001-5965.2017.0285.
  24. Y. Shu, J. Jianguo, L. Junjie, L. Yunlong, Z. Zhongzheng, L. Cong, Fault diagnosis and tolerance control of five-level nested NPP converter using wavelet packet and LSTM, IEEE Trans. Power Electron. 35 (2020) 1907-1921, https://doi.org/10.1109/TPEL.2019.2921677.
  25. S. Mirjalili, S.M. Mirjalili, A. Lewis, Grey wolf optimizer, Adv. Eng. Software 69 (2014) 46-61, https://doi.org/10.1016/j.advengsoft.2013.12.007.
  26. A. Mahmoudi, I. Jlassi, A.J.M. Cardoso, K. Yahia, Model free predictive current control based on a grey wolf optimizer for synchronous reluctance motors, Electronics (Switzerland) 11 (2022), https://doi.org/10.3390/electronics11244166.
  27. Z. Jiang, Fault Diagnosis and Prediction of Analog Filter Based on Deep Learning, Harbin Institute of Technology, 2019, https://doi.org/10.27061/d.cnki.ghgdu.2019.002320.