Rolling Bearing Fault Diagnosis Using Improved Deep Residual Shrinkage Networks

Zhijin Zhang; He Li; Lei Chen; Ping Han

doi:10.1155/2021/9942249

journal article Open Access Jan 01, 2021

Rolling Bearing Fault Diagnosis Using Improved Deep Residual Shrinkage Networks

Zhijin Zhang

He Li

Lei Chen

Ping Han

Shock and Vibration Vol. 2021 No. 1 · Wiley

View at Publisher Save 10.1155/2021/9942249

Abstract

To improve feature learning ability and accurately diagnose the faults of rolling bearings under a strong background noise environment, we present a new shrinkage function named leaky thresholding to replace the soft thresholding in the deep residual shrinkage networks (DRSNs). In this work, we discover that such improved deep residual shrinkage networks (IDRSNs) can be realized by using a group searching method to optimize the slope value of leaky thresholding, and leaky thresholding in the IDRSNs can more effectively eliminate the noise of signal features. We highlight that our techniques can significantly improve the performance on various fundamental tasks. Experimental results show that IDRSNs achieve better fault diagnosis results on noised vibration signals compared with DRSNs. Moreover, we also provide a normalized processing to further improve the fault diagnosing accuracy of rolling bearing under a strong background noise environment.

Topics

No keywords indexed for this article. Browse by subject →

References

35

[1]

10.1016/j.ymssp.2019.106583

[2]

10.1109/tim.2021.3059500

[3]

10.1109/tii.2019.2949000

[4]

10.1016/j.ymssp.2018.08.056

[5]

10.1016/j.ymssp.2018.10.016

[6]

10.1016/j.ymssp.2016.11.003

[7]

Hou M. X. "Stator-winding incipient shorted-turn fault detection for motor system in motorized spindle using modified interval observers" IEEE Transactions on Instrumentation and Measurement (2020)

[8]

Artificial intelligence for fault diagnosis of rotating machinery: A review

Ruonan Liu, Boyuan Yang, Enrico Zio et al.

Mechanical Systems and Signal Processing 10.1016/j.ymssp.2018.02.016

[9]

10.1016/j.jsv.2018.03.032

[10]

10.1007/s12206-018-1211-8

[11]

10.1016/j.ymssp.2017.01.043

[12]

10.1016/j.ymssp.2016.08.005

[13]

10.1109/tie.2016.2519325

[14]

10.1109/access.2017.2717492

[15]

10.1016/j.ymssp.2017.06.027

[16]

An enhancement denoising autoencoder for rolling bearing fault diagnosis

Zong Meng, Xuyang Zhan, Jing Li et al.

Measurement 10.1016/j.measurement.2018.08.010

[17]

10.1109/tim.2017.2759418

[18]

10.1016/j.measurement.2019.01.063

[19]

10.1016/j.ymssp.2020.107233

[20]

10.1016/j.neucom.2018.04.048

[21]

10.1016/j.isatra.2017.03.017

[22]

10.1016/j.ymssp.2017.08.002

[23]

10.1109/tie.2017.2745473

[24]

10.1016/j.neucom.2017.01.032

[25]

10.1016/j.ymssp.2020.106683

[26]

10.1007/s11265-018-1378-3

[27]

10.1016/j.neucom.2018.03.014

[28]

10.1016/j.ymssp.2018.03.025

[29]

Reliable fault diagnosis of bearings with varying rotational speeds using envelope spectrum and convolution neural networks

Dileep K. Appana, Alexander Prosvirin, Jong-Myon Kim

Soft Computing 10.1007/s00500-018-3256-0

[30]

Deep Residual Learning for Image Recognition

Kaiming He, Xiangyu Zhang, Shaoqing Ren et al.

2016 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2016.90

[31]

10.1016/j.isatra.2018.12.025

[32]

10.1109/tie.2017.2762639

[33]

10.1016/j.ymssp.2019.02.055

[34]

10.1109/access.2018.2888842

[35]

10.1109/tii.2019.2943898

Metrics

12

Citations

35

References

Details

Published: Jan 01, 2021
Vol/Issue: 2021(1)
License: View

Authors

Z

Zhijin Zhang

Xuefeng Mountain Energy Equipment Safety National Observation and Research Station, Chongqing University, Chongqing 400044, China

Biological E (India)

Funding

National Natural Science Foundation of China Award: 51675091

Cite This Article

Zhijin Zhang, He Li, Lei Chen, et al. (2021). Rolling Bearing Fault Diagnosis Using Improved Deep Residual Shrinkage Networks. Shock and Vibration, 2021(1). https://doi.org/10.1155/2021/9942249

Rolling Bearing Fault Diagnosis Using Improved Deep Residual Shrinkage Networks

You May Also Like