Improved deep residual shrinkage network used for bearing fault diagnosis

被引：0
|
作者：
Tang S. [1 ]
Tong J. [1 ,2 ]
Zheng J. [1 ]
Pan H. [1 ]
Wu Y. [1 ]
机构：
[1] School of Mechanical Engineering, Anhui University of Technology, Ma'anshan
[2] Anhui Province Engineering Lahoratory of Intelligent Demolition Equipment, Ma'anshan
来源：
Zhendong yu Chongji/Journal of Vibration and Shock | 2023年 / 42卷 / 18期
关键词：
adaptive slope block; deep residual shrinkage network; fault diagnosis; rolling bearing; semi-soft threshold function;
D O I：
10.13465/j.cnki.jvs.2023.018.024
中图分类号：
学科分类号：
摘要：
Aiming at the signal distortion problem caused by the deep residual shrinkage network (DRSN) in the noise reduction process, an improved deep residual shrinkage network (IDRSN) was proposed and applied to the fault diagnosis of rolling bearings. Firstly, an improved semi-soft threshold function (ISSTF) was introduced to solve the problem of identity deviation and eliminate the signal distortion caused by the soft threshold function. Then, a semi-soft threshold block (SSTB) and an adaptive slope block (ASB) were designed to construct an improved residual shrinkage building unit (IRSBU), which was used to adaptively set the optimal threshold value and further correct the output. Finally, the proposed method was applied to the fault diagnosis of rolling bearings in two different operating conditions. The results show that the proposed method has higher classification accuracy and robustness compared with existing methods, and is more effective for fault diagnosis in variable speed conditions. © 2023 Chinese Vibration Engineering Society. All rights reserved.
引用
下载
收藏
页码：217 / 285
页数：68
相关论文
共 23 条
  • [1] YAN W, Fault diagnosis of roller bearings b a s e d on the variational mode decomposition and S V M [ J ], Journal o f Vibration a n d S h o c k, 2, pp. 252-256
  • [2] MA J, XU F, HUANG K, Et al., GNAR - GARCH model and its application in feature extraction for rolling bearing fault diagnosis [ J ], Mechanical Systems and Signal Processing, 93, pp. 175-203, (2017)
  • [3] HINTON G E, SALAKHUTDINOV R R., Reducing the dimensionality of data with neural networks [ J ], Science, 313, 5786, pp. 504-507, (2006)
  • [4] ELSISI M, TRAN M Q, MAHMOUD K, Et al., Effective IoTbased deep learning platform for online fault diagnosis of power transformers against cyberattack and data uncertainties [ J ], Measurement, 190, (2022)
  • [5] LI C H, ZHANG W, PENG G L, Et al., Bearing fault diagnosis using fully-connected winner-take-all autoencoder [J], IEEE Access, 6, pp. 6103-6115, (2017)
  • [6] XU Zifei, JIN Jiangtao, LI Chun, New method for the fault diagnosis of rolling bearings based on a multiscale convolutional neural network [ J ], Journal of Vibration and Shock, 2, pp. 47-52
  • [7] LEI Yaguo, JIA Feng, KONG Detong, Et al., Opportunities and challenges of machinery intelligent fault diagnosis in big data era [ J ], Journal of Mechanical Engineering, 5 4, pp. 94-104, (2018)
  • [8] ZHENG J D, PAN H Y, TONG J Y, Et al., Generalized refined composite multiscale fuzzy entropy and multi-cluster feature selection based intelligent fault diagnosis of rolling bearing, ISA Transactions, 123, pp. 136-151, (2022)
  • [9] ZHANG Zhiyu, YIN Aijun, TAN Jian, Improved DBN method with attention mechanism for the fault diagnosis of gearboxes under varying working condition [ J ], Journal of Vibration and Shock, 40, 14, pp. 212-220, (2021)
  • [10] SHAO H D, JIANG H K, ZHANG H Z, Et al., Electric locomotive bearing fault diagnosis using a novel convolutional deep belief network [ J ], IEEE Transactions on Industrial Electronics, 2
123