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
. 2024 Jan 7;14(1):743.
doi: 10.1038/s41598-023-50826-6.

Gearbox fault diagnosis method based on lightweight channel attention mechanism and transfer learning

Xuemin Cheng  1 , Shuihai Dou  2 , Yanping Du  1 , Zhaohua Wang  1
Affiliations

Gearbox fault diagnosis method based on lightweight channel attention mechanism and transfer learning

Xuemin Cheng et al. Sci Rep. .

Abstract

In practical engineering, the working conditions of gearbox are complex and variable. In varying working conditions, the performance of intelligent fault diagnosis model is degraded because of limited valid samples and large data distribution differences of gearbox signals. Based on these issues, this research proposes a gearbox fault diagnosis method integrated with lightweight channel attention mechanism, and further realizes the cross-component transfer learning. First, time-frequency distribution of original signals is obtained by wavelet transform. It could intuitively reflect local characteristics of signals. Secondly, based on a local cross-channel interaction strategy, a lightweight efficient channel attention mechanism (LECA) is designed. The kernel size of 1D convolution is affected by channel number and coefficients. Multi-scale feature input is used to retain more detailed features of different dimensions. A lightweight convolutional neural network is constructed. Finally, a transfer learning method is applied to freeze lower structures of the network and fine-tune higher structures of the model using small samples. Through experimental verification, the proposed model could effectively utilize samples. The application of transfer learning could realize accurate and fast fault classification of small samples, and achieve good gearbox fault diagnosis effect under varying working conditions and cross-component conditions.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Architectural details of MBConv module.
Figure 2
Figure 2
Architectural details of Fused-MBConv module.
Figure 3
Figure 3
Architectural details of ECA module.
Figure 4
Figure 4
Architectural details of LECA module.
Figure 5
Figure 5
Fault diagnosis flow of the LECA-EfficientNetV2 transfer learning model.
Figure 6
Figure 6
The wavelet time–frequency images of bearing signals.
Figure 7
Figure 7
The wavelet time–frequency images of gear signals.
Figure 8
Figure 8
The fault diagnosis time for models based on three attention mechanisms.
Figure 9
Figure 9
Accuracy curves of models based on three attention mechanisms for 50 iterations.
Figure 10
Figure 10
Confusion matrix for bearing and gear samples at 20 Hz-0 V working condition.
Figure 11
Figure 11
Classification accuracy of eight transfer learning fault diagnosis models in four tasks.
Figure 12
Figure 12
Fault diagnosis time of eight transfer learning fault diagnosis models in four tasks.
Figure 13
Figure 13
The visualization of samples feature distribution variation using t-SEN.
See this image and copyright information in PMC

References

    1. Yan X, She D, Xu Y, Jia M. Deep regularized variational autoencoder for intelligent fault diagnosis of rotor-bearing system within entire life-cycle process. Knowl-Based. Syst. 2021;226:107142. doi: 10.1016/j.knosys.2021.107142. - DOI
    1. Wang K, Qin F. Fault diagnosis of gearbox based on Fourier Bessel EWT and manifold regularization ELM. Sci. Rep.-UK. 2023;13(1):14486–14486. doi: 10.1038/s41598-023-40369-1. - DOI - PMC - PubMed
    1. Mishra RK, Choudhary A, Fatima S, Mohanty AR, Panigrahi BK. A fault diagnosis approach based on 2D-Vibration imaging for bearing faults. J. Vib. Eng. Technol. 2022;11(7):3121–3134. doi: 10.1007/s42417-022-00735-1. - DOI
    1. Dou S, Liu Y, Du Y, Wang Z, Jia X. Research on feature extraction and diagnosis method of gearbox vibration signal based on VMD and ResNeXt. Int. J. Comput. Int. Sys. 2023;16(1):119. doi: 10.1007/s44196-023-00301-x. - DOI
    1. Liu Y, Dan B, Yi C, Huang T, Zhang F. Self-matching extraction fractional wavelet transform for mechanical equipment fault diagnosis. Meas. Sci. Technol. 2024;35(3):035102. doi: 10.1088/1361-6501/ad108c. - DOI