skip to main content
10.1145/3665348.3665409acmotherconferencesArticle/Chapter ViewAbstractPublication PagesgaiisConference Proceedingsconference-collections
research-article

Enhanced Bearing Fault Diagnosis under Strong Noise: An improved Inception Inverted Residual Ghost ShuffleNet

Published: 03 July 2024 Publication History

Abstract

As an indispensable and easily damaged part in large equipment, bearings were of great significance for their rapid and accurate fault diagnosis. The working environment of bearings was usually harsh and complicated. In order to improve the accuracy of bearing fault diagnosis under strong noise, an improved IRGShuffleNet network structure was proposed. The initial multi-scale structure based on LIBP was innovatively used to extract the shallow feature information of the network. Features were extracted from high-dimensional data using the inverted residual structure, and redundant feature maps were generated in a cheaper way by Ghost convolution. Random depth structure and flooding regularization were used to prevent overfitting of the model. To evaluate the validity of the proposed model, a series of comparative experiments were conducted. Compared with the standard residual network, the accuracy of the model proposed in this paper was improved by 5.90% and 9.72% respectively under -4dB and -10dB noise. The model parameter was reduced from 25.7M to 1.98M, FLOPs were reduced by about 75.2%, and other performance indicators were also improved at different amplitudes. These results showed that the proposed model had good diagnostic adaptability.

References

[1]
Du F M, Li D W, Sa X X, Li C, Yu Y, Li C D, Wang J S, Wang W W. Overview of Friction and Wear Performance of Sliding Bearings. Coatings, 2022, 12(9): 1-15.
[2]
Burdzik R, Ragulskis M, Cao M, Zimroz R, Fakher C, Konieczny Ł, Betta G, Altaf M, Akram T, Khan M A, Iqbal M Z, Munawwar M, Ch I, Hsu C H. A New Statistical Features Based Approach for Bearing Fault Diagnosis Using Vibration Signals. Sensors (Basel, Switzerland), 2022, 22: 1-15.
[3]
Boudiaf R, Abdelkarim B, Issam H. Bearing fault diagnosis in induction motor using continuous wavelet transform and convolutional neural networks. International Journal of Power Electronics and Drive Systems (IJPEDS), 2024: 1-12.
[4]
Szegedy C, Ioffe S, Vanhoucke V, Alemi A A, Aaai. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning; proceedings of the 31st AAAI Conference on Artificial Intelligence, San Francisco, CA, F Feb 04-09, 2017. 4278-4284.
[5]
Howard A, Sandler M, Chu G, Chen L C, Chen B, Tan M X, Wang W J, Zhu Y K, Pang R M, Vasudevan V, Le Q V, Adam H, Ieee. Searching for MobileNetV3; proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, SOUTH KOREA, F Oct 27-Nov 02, 2019. 1314-1324.
[6]
Ma N N, Zhang X Y, Zheng H T, Sun J. ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design; proceedings of the 15th European Conference on Computer Vision (ECCV), Munich, GERMANY, F Sep 08-14, 2018. 122-138.
[7]
Tan M X, Le Q V. EfficientNetV2: Smaller Models and Faster Training; proceedings of the International Conference on Machine Learning (ICML), Electr Network, F Jul 18-24, 2021. 7102-7110.
[8]
Luo Z Y, Tan H K, Dong X, Zhu G M, Li J L. A fault diagnosis method for rotating machinery with variable speed based on multi-feature fusion and improved ShuffleNet V2. Measurement Science and Technology, 2023, 34(3): 1-5.
[9]
Gao Z T, Wang L M, Wu G S, Ieee. LIP: Local Importance-based Pooling; proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, SOUTH KOREA, F Oct 27-Nov 02, 2019. 3354-3363.
[10]
Zhang R. Making Convolutional Networks Shift-Invariant Again; proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, F Jun 09-15, 2019. 1-16.
[11]
Han K, Wang Y H, Tian Q, Guo J Y, Xu C J, Xu C, Ieee. GhostNet: More Features from Cheap Operations; proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Electr Network, F Jun 14-19, 2020. 1577-1586.
[12]
Huang G, Sun Y, Liu Z, Sedra D, Weinberger K Q. Deep Networks with Stochastic Depth; proceedings of the 14th European Conference on Computer Vision (ECCV), Amsterdam, NETHERLANDS, F Oct 08-16, 2016. 646-661.
[13]
Ishida T, Yamane I, Sakai T, Niu G, Sugiyama M. Do We Need Zero Training Loss After Achieving Zero Training Error?; proceedings of the International Conference on Machine Learning (ICML), Electr Network, F Jul 13-18, 2020. 1-27.
[14]
Smith W A, Randall R B. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study. Mechanical Systems and Signal Processing, 2015, 64-65: 100-131.
[15]
Łuczak D. Mechanical Vibrations Analysis in Direct Drive Using CWT with Complex Morlet Wavelet. Power Electronics and Drives, 2023, 8: 65-73.
[16]
Ding C, Zhang M, Gu Y. Study on image quality Control Method based on Gaussian Noise. Journal of Physics: Conference Series, 2021, 2029: 1-8.

Index Terms

  1. Enhanced Bearing Fault Diagnosis under Strong Noise: An improved Inception Inverted Residual Ghost ShuffleNet

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    GAIIS '24: Proceedings of the 2024 International Conference on Generative Artificial Intelligence and Information Security
    May 2024
    439 pages
    ISBN:9798400709562
    DOI:10.1145/3665348
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 03 July 2024

    Permissions

    Request permissions for this article.

    Check for updates

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    GAIIS 2024

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 11
      Total Downloads
    • Downloads (Last 12 months)11
    • Downloads (Last 6 weeks)1
    Reflects downloads up to 17 Feb 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media