Rolling Bearing Fault Diagnosis Based on CBAM-WDCNN
DOI:
https://doi.org/10.54097/ax9dcm05Keywords:
Bearing fault diagnosis; deep learning; convolutional neural network; convolutional neural attention mechanism.Abstract
Rolling bearing fault diagnosis methods based on convolutional neural networks (CNNs) have demonstrated excellent capabilities in processing complex nonlinear signals. Among them, the one-dimensional convolutional neural network greatly accelerates the signal processing process by directly processing the one-dimensional time-series signal and simplifying the input of the model. However, the traditional 1D convolutional neural network has problems such as poor feature recognition. In this paper, we propose a model based on the fusion of the attention mechanism CBAM and the deep convolutional neural network with a wide kernel in the first layer (WDCNN), which emphasizes the key features and suppresses the irrelevant noises, and significantly improves the model's recognition ability for fault features. The improved method is compared with other diagnostic algorithms to verify its higher accuracy and more stable training process.
Downloads
References
[1] Li X, Ma Z, Yuan Z, et al. (2024). A review on convolutional neural network in rolling bearing fault diagnosis[J]. Measurement Science and Technology, 35(7). DOI:10.1088/1361-6501/AD356E.
[2] Sha M, Liu L. (2015). A review of bearing fault diagnosis techniques based on vibration signals[J]. Bearing, (09):59-63. https://link.cnki.net/doi/10.19533/j.issn1000-3762.2015.09.017
[3] Li M, Yang J, Wang X. (2015). Information entropy based cyclic spectrum analysis method and its application in rolling bearing fault diagnosis[J]. Journal of Vibration Engineering, 28(01):164-174. https://link.cnki.net/doi/10.16385/j.cnki.issn.1004-4523.2015.01.021
[4] Qu J, Zhang Z, Gong T. (2015). A novel intelligent method for mechanical fault diagnosis based on dual-tree complex wavelet packet transform and multiple classifier fusion[J]. Neurocomputing, 171837-853. DOI:10.1016/j.neucom.2015.07.020.
[5] Keskes H ,Braham A ,Lachiri Z. (2013). Broken rotor bar diagnosis in induction machines through stationary wavelet packet transform and multiclass wavelet SVM[J]. Electric Power Systems Research, 97151-157. DOI:10.1016/j.epsr.2012.12.013.
[6] Qu J, Yu L, Yuan T, et al. (2018). Adaptive fault diagnosis algorithm for rolling bearings based on one-dimensional convolutional neural network[J]. Journal of Instrumentation, 39(07):134-143. DOI:10.19650/j.cnki.cjsi.J1803286.
[7] Zhang W. (2018). Research on bearing fault diagnosis algorithm based on convolutional neural network [D]. Harbin Institute of Technology.
[8] Yao Q, Bie S, Yu J, et al. (2022). A bearing fault diagnosis method combining improved Inception V2 module and CBAM[J]. Journal of Vibration Engineering, 35(04):949-957. https://link.cnki.net/doi/10.16385/j.cnki.issn.1004-4523.2022.04.019
[9] Li J, Ma Y, Hu X, et al. (2023). Wind turbine bearing fault diagnosis based on CBAM-InceptionV2-dual-stream CNN[J]. Intelligent Power, 51(06):28-33.
[10] Xu S, Yuan R, Lv Y, et al. (2023). A novel fault diagnosis approach of rolling bearing using intrinsic feature extraction and CBAM-enhanced InceptionNet[J]. Measurement Science and Technology, 34(10). DOI:10.1088/1361-6501/ACE19C.
[11] Du X,Gong B,Yu P,et al. (2022). Fault diagnosis of analog circuits based on CBAM-CNN[J]. Control and Decision Making, 37(10):2609-2618. DOI:10.13195/j.kzyjc.2021.1111.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.