Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Oct 12;21(20):6754.
doi: 10.3390/s21206754.

A Novel Intelligent Fault Diagnosis Method for Rolling Bearings Based on Wasserstein Generative Adversarial Network and Convolutional Neural Network under Unbalanced Dataset

Hongtao Tang  1 , Shengbo Gao  1 , Lei Wang  1 , Xixing Li  2 , Bing Li  1 , Shibao Pang  1
Affiliations

A Novel Intelligent Fault Diagnosis Method for Rolling Bearings Based on Wasserstein Generative Adversarial Network and Convolutional Neural Network under Unbalanced Dataset

Hongtao Tang et al. Sensors (Basel). .

Abstract

Rolling bearings are widely used in industrial manufacturing, and ensuring their stable and effective fault detection is a core requirement in the manufacturing process. However, it is a great challenge to achieve a highly accurate rolling bearing fault diagnosis because of the severe imbalance and distribution differences in fault data due to weak early fault features and interference from environmental noise. An intelligent fault diagnosis strategy for rolling bearings based on grayscale image transformation, a generative adversative network, and a convolutional neural network was proposed to solve this problem. First, the original vibration signal is converted into a grayscale image. Then more training samples are generated using GANs to solve severe imbalance and distribution differences in fault data. Finally, the rolling bearing condition detection and fault identification are carried out by using SECNN. The availability of the method is substantiated by experiments on datasets with different data imbalance ratios. In addition, the superiority of this diagnosis strategy is verified by comparing it with other mainstream intelligent diagnosis techniques. The experimental result demonstrates that this strategy can reach more than 99.6% recognition accuracy even under substantial environmental noise interference or changing working conditions and has good stability in the presence of a severe imbalance in fault data.

Keywords: convolutional neural networks (CNN); data imbalance; generative adversarial networks (GAN); intelligent fault diagnosis; rolling bearings.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Schematic diagram of the sliding window fetching method.
Figure 2
Figure 2
Signal to image conversion method. (a) Signal Interception Using a Sliding Window, (b) Combination of Vibration Signal Sequences, (c) Grayscale Image Transformation, (d) Grayscale Image.
Figure 3
Figure 3
The structure of a GAN.
Figure 4
Figure 4
The classical structure of CNN networks.
Figure 5
Figure 5
The training process of CNN.
Figure 6
Figure 6
(a) SE network. (b) SECNN module.
Figure 7
Figure 7
The diagnostic framework based on WGAN-GP and SECNN.
Figure 8
Figure 8
Flowchart of WGAN-GP and SECNN implementation.
Figure 9
Figure 9
The rolling bearing fault simulation test platform.
Figure 10
Figure 10
The generator loss function value change curve.
Figure 11
Figure 11
The discriminator loss function value change curve.
Figure 12
Figure 12
Comparison of batch size experiment and learning rate size.
Figure 13
Figure 13
A specific architecture of SECNN.
Figure 14
Figure 14
Multi-class confusion matrix of the presented method.
Figure 15
Figure 15
Feature visualization via t-SNE: (a) original signal; (b) conv layer1; (c) conv layer2; (d) conv layer3; (e) FC layer.
Figure 16
Figure 16
The accuracy curves of the proposed model training process.
Figure 17
Figure 17
Comparison of accuracy testing under different noise environments.
Figure 18
Figure 18
Contrast experiment under ten imbalanced cases.
See this image and copyright information in PMC

References

    1. Zhou X., Li Y., Jiang L., Zhou L. Fault feature extraction for rolling bearings based on parameter-adaptive variational mode decomposition and multi-point optimal minimum entropy deconvolution. Measurement. 2021;173:108469. doi: 10.1016/j.measurement.2020.108469. - DOI
    1. Li J., Yao X., Wang H., Zhang J. Periodic impulses extraction based on improved adaptive VMD and sparse code shrinkage denoising and its application in rotating machinery fault diagnosis. Mech. Syst. Signal Process. 2019;126:568–589. doi: 10.1016/j.ymssp.2019.02.056. - DOI
    1. Shenfield A., Howarth M. A Novel Deep Learning Model for the Detection and Identification of Rolling Element-Bearing Faults. Sensors. 2020;20:5112. doi: 10.3390/s20185112. - DOI - PMC - PubMed
    1. Wu Y.K., Jiang B., Wang Y.L. Incipient winding fault detection and diagnosis for squirrel-cage induction motors equipped on CRH trains. ISA Trans. 2020;99:488–495. doi: 10.1016/j.isatra.2019.09.020. - DOI - PubMed
    1. Yu W., Xu H., Han X., Chen Y., Zhu M. Fault-Tolerant Control for Dynamic Positioning Vessel With Thruster Faults Based on the Neural Modified Extended State Observer. IEEE Trans. Syst. Man Cybern.-Syst. 2021;51:5905–5917. doi: 10.1109/TSMC.2019.2956806. - DOI