Study of diagnosis for rotating machinery in advanced nuclear reactor based on deep learning model

被引:2
作者
Sun, Yuanli [1 ]
Wang, Hang [2 ]
机构
[1] Tsinghua Univ, Nucl Res Inst, Beijing, Peoples R China
[2] Harbin Engn Univ, Nucl Sci & Technol, Harbin, Peoples R China
关键词
fault diagnosis model; deep learning; rotating machine; advanced nuclear reactor; improved transformer model; FAULT-DIAGNOSIS;
D O I
10.3389/fenrg.2023.1210703
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Many types of rotating mechanical equipment, such as the primary pump, turbine, and fans, are key components of fourth-generation (Gen IV) advanced reactors. Given that these machines operate in challenging environments with high temperatures and liquid metal corrosion, accurate problem identification and health management are essential for keeping these machines in good working order. This study proposes a deep learning (DL)-based intelligent diagnosis model for the rotating machinery used in fast reactors. The diagnosis model is tested by identifying the faults of bearings and gears. Normalization, augmentation, and splitting of data are applied to prepare the datasets for classification of faults. Multiple diagnosis models containing the multi-layer perceptron (MLP), convolutional neural network (CNN), recurrent neural network (RNN), and residual network (RESNET) are compared and investigated with the Case Western Reserve University datasets. An improved Transformer model is proposed, and an enhanced embeddings generator is designed to combine the strengths of the CNN and transformer. The effects of the size of the training samples and the domain of data preprocessing, such as the time domain, frequency domain, time-frequency domain, and wavelet domain, are investigated, and it is found that the time-frequency domain is most effective, and the improved Transformer model is appropriate for the fault diagnosis of rotating mechanical equipment. Because of the low probability of the occurrence of a fault, the imbalanced learning method should be improved in future studies.
引用
收藏
页数:12
相关论文
共 20 条
  • [1] LEARNING LONG-TERM DEPENDENCIES WITH GRADIENT DESCENT IS DIFFICULT
    BENGIO, Y
    SIMARD, P
    FRASCONI, P
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (02): : 157 - 166
  • [2] A Review of Artificial Intelligence Algorithms Used for Smart Machine Tools
    Chang, Chih-Wen
    Lee, Hau-Wei
    Liu, Chein-Hung
    [J]. INVENTIONS, 2018, 3 (03)
  • [3] Donahue J, 2014, PR MACH LEARN RES, V32
  • [4] Deep learning enabled intelligent fault diagnosis: Overview and applications
    Duan, Lixiang
    Xie, Mengyun
    Wang, Jinjiang
    Bai, Tangbo
    [J]. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2018, 35 (05) : 5771 - 5784
  • [5] A Comprehensive Survey of Prognostics and Health Management Based on Deep Learning for Autonomous Ships
    Ellefsen, Andre Listou
    Aesoy, Vilmar
    Ushakov, Sergey
    Zhang, Houxiang
    [J]. IEEE TRANSACTIONS ON RELIABILITY, 2019, 68 (02) : 720 - 740
  • [6] Learning to forget: Continual prediction with LSTM
    Gers, FA
    Schmidhuber, J
    Cummins, F
    [J]. NEURAL COMPUTATION, 2000, 12 (10) : 2451 - 2471
  • [7] Hamadache M., 2019, JMST ADV, V1, P125, DOI DOI 10.1007/S42791-019-0016-Y
  • [8] Deep Residual Learning for Image Recognition
    He, Kaiming
    Zhang, Xiangyu
    Ren, Shaoqing
    Sun, Jian
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 770 - 778
  • [9] Hochreiter S., 1997, NOV, V15, P8, DOI [10.1007/978-3-642-24797-2, DOI 10.1007/978-3-642-24797-2]
  • [10] LeCun Y, 1995, HDB BRAIN THEORY NEU, V3361, DOI 10.5555/303568.303704