A semi-supervised fault diagnosis model based on a teacher-student network

被引：0
|
作者：
Gao Y. [1 ]
Fu Z. [1 ]
Xie Y. [2 ]
Wang S. [1 ]
机构：
[1] Key Laboratory of Power Station Energy Transfer Conversion and System of Ministry of Education, North China Electric Power University, Beijing
[2] College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Beijing
来源：
Zhendong yu Chongji/Journal of Vibration and Shock | 2024年 / 43卷 / 04期
关键词：
continuous wavelet transform; fault diagnosis; rotating machinery; semi-supervised learning;
D O I：
10.13465/j.cnki.jvs.2024.04.018
中图分类号：
学科分类号：
摘要：
A semi-supervised learning method based on the continuous wavelet transform anda teacher-student network was proposed for fault diagnosis of rotating machinery, aiming to address the problems of network overfitting, low fault diagnosis accuracy, and underutilization of large amounts of unlabeled data when neural network models are used with limited labeled samples. The method is based on an improved Lenet-5 convolutional neural network model, which establishes a student network model and a teacher network model with the same structure and initialization parameters. First, the vibration signal of rotating machinery wastransformed by continuous wavelet transform into a three-dimensional time-frequency image. Then, pseudo-labels weregenerated using the prediction results of the teacher model, and these pseudo-labels werecombined with the real labels to train the student network. At the same time, the teacher network model parameters wereupdated using an exponential weighted moving average algorithm. Experimental results show that compared with the pure supervised learning model, the proposed algorithm can significantly improve the stability of the model training process and the accuracy of fault diagnosis with limited labeled samples. © 2024 Chinese Vibration Engineering Society. All rights reserved.
引用
下载
收藏
页码：150 / 157
页数：7
相关论文
共 17 条
  • [1] Lei J, Liu C, Jiang D., Fault diagnosis of wind turbine based on Long Short-term memory networks, Renewable energy, 133, pp. 422-432, (2019)
  • [2] Zhao R, Wang D, Yan R, Et al., Machine health monitoring using local feature-based gated recurrent unit networks, IEEE Transactions on Industrial Electronics, 65, 2, pp. 1539-1548, (2017)
  • [3] SHI Hong-mei, ZHENG Chang-chang, SI Jin, Et al., Fault diagnosis algorithm of rotating machinery based on dynamic weighted multiscale residual network[J], ournal of vibration and shock, 41, 23, pp. 67-74, (2022)
  • [4] Mo Z, Zhang Z, Tsui K L., The variational kernel-based 1-D convolutional neural network for achinery fault diagnosis, IEEE Transactions on Instrumentation and Measurement, 70, pp. 1-10, (2021)
  • [5] Yoo Y, Baek J G., A novel image feature for the emaining useful lifetime prediction of bearings based on continuous wavelet transform and convolutional neural network[J], Applied Sciences, 7, (2018)
  • [6] Wu J, Zhao Z, Sun C, Et al., Few-shot transfer learning for intelligent fault diagnosis of machine, Measurement, 166, (2020)
  • [7] SU Yuan-hao, MENG Liang, XU Tong-le, Et al., Wind turbine gearbox fault diagnosis method for optimized WGAN with unbalanced data sets[J], Acta energiae solaris sinica, 43, 11, pp. 148-155, (2022)
  • [8] Wen L, Gao L, Li X., A new deep transfer learning based on sparse auto-encoder for fault diagnosis, IEEE Transactions on systems, man, and ybernetics: systems, 49, 1, pp. 136-144, (2017)
  • [9] Shao H, Xia M, Han G, Et al., Intelligent fault diagnosis of rotor-bearing system under varying working onditions with modified transfer convolutional neural network and thermal images, IEEE Transactions on Industrial Informatics, 17, 5, pp. 3488-3496, (2020)
  • [10] XING Xiao-song, GUO Wei, Intelligent iagnosis method for bearings with few labelled samples based on an improved semi-supervised learning-based generative adversarial network, ournal of vibration and shock, 41, 22, pp. 184-192, (2022)
12