Adaptive hybrid attention mechanism deep residual threshold networks for bearing fault diagnosis under noisy environments

Yan Wang; Kangwen Sun; Yongkao Li; Haoquan Liang; Yan Wang; Kangwen Sun; Yongkao Li; Haoquan Liang

doi:10.3934/era.2025237

Electronic Research Archive

2025, Volume 33, Issue 9: 5301-5322. doi: 10.3934/era.2025237

Previous Article Next Article

Research article

Adaptive hybrid attention mechanism deep residual threshold networks for bearing fault diagnosis under noisy environments

1.
School of Aeronautic Science and Engineering, Beihang University, Beijing 100191, China
2.
Institute of Unmanned System, Beihang University, Beijing 100191, China

Received: 28 June 2025 Revised: 21 August 2025 Accepted: 05 September 2025 Published: 10 September 2025

Intelligent bearing fault diagnosis based on deep learning has immense potential. However, improving the noise immunity, generality, and accuracy of fault diagnosis methods is still challenging. This paper proposes a novel adaptive hybrid attention mechanism deep residual threshold network (AHA-RTN) for bearing fault diagnosis under various noise conditions. First, channel-wise and spatial attention were both integrated into residual blocks to capture multiscale information. Hybrid attention was obtained using the proposed adaptive attention module, which computes adjustment coefficients of each attentional mechanism. Next, a novel noise reduction activation function based on soft thresholding was incorporated to suppress noise. Finally, the method was validated on two distinct bearing datasets under various noise conditions. The results show that the proposed AHA-RTN has better noise immunity and accuracy than the other advanced multiscale convolutional neural networks.
- deep learning,
- fault diagnosis,
- attention mechanism,
- threshold denoising,
- deep residual threshold network
Citation: Yan Wang, Kangwen Sun, Yongkao Li, Haoquan Liang. Adaptive hybrid attention mechanism deep residual threshold networks for bearing fault diagnosis under noisy environments[J]. Electronic Research Archive, 2025, 33(9): 5301-5322. doi: 10.3934/era.2025237

Related Papers:

Abstract

Intelligent bearing fault diagnosis based on deep learning has immense potential. However, improving the noise immunity, generality, and accuracy of fault diagnosis methods is still challenging. This paper proposes a novel adaptive hybrid attention mechanism deep residual threshold network (AHA-RTN) for bearing fault diagnosis under various noise conditions. First, channel-wise and spatial attention were both integrated into residual blocks to capture multiscale information. Hybrid attention was obtained using the proposed adaptive attention module, which computes adjustment coefficients of each attentional mechanism. Next, a novel noise reduction activation function based on soft thresholding was incorporated to suppress noise. Finally, the method was validated on two distinct bearing datasets under various noise conditions. The results show that the proposed AHA-RTN has better noise immunity and accuracy than the other advanced multiscale convolutional neural networks.

References

[1]	W. Huang, Z. Li, X. Ding, D. He, Q. Wu, J. Liu, Digital-analog driven multi-scale transfer for smart bearing fault diagnosis, Eng. Appl. Artif. Intell. , 137 (2024), 109186. https://doi.org/10.1016/j.engappai.2024.109186 doi: 10.1016/j.engappai.2024.109186
[2]	J. Tong, S. Tang, Y. Wu, H. Pan, J. Zheng, A fault diagnosis method of rolling bearing based on improved deep residual shrinkage networks, Measurement, 206 (2023), 112282. https://doi.org/10.1016/j.measurement.2022.112282 doi: 10.1016/j.measurement.2022.112282
[3]	B. Pang, M. Nazari, G. Tang, Recursive variational mode extraction and its application in rolling bearing fault diagnosis, Mech. Syst. Signal Process. , 165 (2022), 108321. https://doi.org/10.1016/j.ymssp.2021.108321 doi: 10.1016/j.ymssp.2021.108321
[4]	F. Li, L. Wang, D. Wang, J. Wu, H. Zhao, An adaptive multiscale fully convolutional network for bearing fault diagnosis under noisy environments, Measurement, 216 (2023), 112993. https://doi.org/10.1016/j.measurement.2023.112993 doi: 10.1016/j.measurement.2023.112993
[5]	Y. Li, M. Xu, W. Huang, M. J. Zuo, L. Liu, An improved EMD method for fault diagnosis of rolling bearing, in 2016 Prognostics and System Health Management Conference (PHM-Chengdu), (2016), 1–5. https://doi.org/10.1109/PHM.2016.7819842
[6]	J. Zheng, M. Su, W. Ying, J. Tong, Z. Pan, Improved uniform phase empirical mode decomposition and its application in machinery fault diagnosis, Measurement, 179 (2021), 109425. https://doi.org/10.1016/j.measurement.2021.109425 doi: 10.1016/j.measurement.2021.109425
[7]	K. Zhang, C. Ma, Y. Xu, P. Chen, J. Du, Feature extraction method based on adaptive and concise empirical wavelet transform and its applications in bearing fault diagnosis, Measurement, 172 (2021), 108976. https://doi.org/10.1016/j.measurement.2021.108976 doi: 10.1016/j.measurement.2021.108976
[8]	H. Hu, Y. Lv, R. Yuan, S. Xu, W. Zhu, A novel vibro-acoustic fault diagnosis approach of planetary gearbox using intrinsic wavelet integrated GE-EfficientNet, Meas. Sci. Technol. , 35 (2024), 025131. https://doi.org/10.1088/1361-6501/ad0afe doi: 10.1088/1361-6501/ad0afe
[9]	K. Dragomiretskiy, D. Zosso, Variational mode decomposition, IEEE Trans. Signal Process. , 62 (2014), 531–544. https://doi.org/10.1109/TSP.2013.2288675 doi: 10.1109/TSP.2013.2288675
[10]	S. Chauhan, G. Vashishtha, R. Kumar, R. Zimroz, M. K. Gupta, P. Kundu, An adaptive feature mode decomposition based on a novel health indicator for bearing fault diagnosis, Measurement, 226 (2024), 114191. https://doi.org/10.1016/j.measurement.2024.114191 doi: 10.1016/j.measurement.2024.114191
[11]	B. Zheng, M. Zhu, X. Guo, J. Ou, J. Yuan, Path planning of stratospheric airship in dynamic wind field based on deep reinforcement learning, Aerosp. Sci. Technol. , 150 (2024), 109173. https://doi.org/10.1016/j.ast.2024.109173 doi: 10.1016/j.ast.2024.109173
[12]	H. Hu, B. Tang, X. Gong, W. Wei, H. Wang, Intelligent fault diagnosis of the high-speed train with big data based on deep neural networks, IEEE Trans. Ind. Inf. , 13 (2017), 2106–2116. https://doi.org/10.1109/TII.2017.2683528 doi: 10.1109/TII.2017.2683528
[13]	C. Liu, X. Li, X. Chen, S. Khan, Neuromorphic computing-enabled generalized machine fault diagnosis with dynamic vision, Adv. Eng. Inf. , 65 (2025), 103300. https://doi.org/10.1016/j.aei.2025.103300 doi: 10.1016/j.aei.2025.103300
[14]	W. Zhang, M. Xu, H. Yang, X. Wang, S. Zheng, X. Li, Data-driven deep learning approach for thrust prediction of solid rocket motors, Measurement, 225 (2024), 114051. https://doi.org/10.1016/j.measurement.2023.114051 doi: 10.1016/j.measurement.2023.114051
[15]	L. Yang, Z. Yang, S. Song, F. Li, C. P. Chen, Twin broad learning system for fault diagnosis of rotating machinery, IEEE Trans. Instrum. Meas. , 72 (2023), 1–12. https://doi.org/10.1109/TIM.2023.3259022 doi: 10.1109/TIM.2023.3259022
[16]	Z. Hei, W. Sun, H. Yang, M. Zhong, Y. Li, A. Kumar, et al., Novel domain-adaptive Wasserstein generative adversarial networks for early bearing fault diagnosis under various conditions, Reliab. Eng. Syst. Saf. , 257 (2025), 110847. https://doi.org/10.1016/j.ress.2025.110847 doi: 10.1016/j.ress.2025.110847
[17]	X. Li, X. Wu, T. Wang, Y. Xie, F. Chu, Fault diagnosis method for imbalanced data based on adaptive diffusion models and generative adversarial networks, Eng. Appl. Artif. Intell. , 147 (2025), 110410. https://doi.org/10.1016/j.engappai.2025.110410 doi: 10.1016/j.engappai.2025.110410
[18]	W. Zhang, N. Jiang, S. Yang, X. Li, Federated transfer learning for remaining useful life prediction in prognostics with data privacy, Meas. Sci. Technol. , 36 (2025), 076107. https://doi.org/10.1088/1361-6501/ade552 doi: 10.1088/1361-6501/ade552
[19]	X. Li, S. Xiao, Q. Li, L. Zhu, T. Wang, F. Chu, The bearing multi-sensor fault diagnosis method based on a multi-branch parallel perception network and feature fusion strategy, Reliab. Eng. Syst. Saf. , 261 (2025), 111122. https://doi.org/10.1016/j.ress.2025.111122 doi: 10.1016/j.ress.2025.111122
[20]	K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2016), 770–778. https://doi.org/10.1109/CVPR.2016.90
[21]	G. Huang, Z. Liu, L. V. D. Maaten, K. Q. Weinberger, Densely connected convolutional networks, in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2017), 2261–2269. https://doi.org/10.1109/CVPR.2017.243
[22]	W. Zhang, X. Li, Q. Ding, Deep residual learning-based fault diagnosis method for rotating machinery, ISA Trans. , 95 (2019), 295–305. https://doi.org/10.1016/j.isatra.2018.12.025 doi: 10.1016/j.isatra.2018.12.025
[23]	M. Zhao, B. Tang, L. Deng, M. Pecht, Multiple wavelet regularized deep residual networks for fault diagnosis, Measurement, 152 (2020), 107331. https://doi.org/10.1016/j.measurement.2019.107331 doi: 10.1016/j.measurement.2019.107331
[24]	X. Zheng, P. Yang, K. Yan, Y. He, Q. Yu, M. Li, Rolling bearing fault diagnosis based on multiple wavelet coefficient dimensionality reduction and improved residual network, Eng. Appl. Artif. Intell. , 133 (2024), 108087. https://doi.org/10.1016/j.engappai.2024.108087 doi: 10.1016/j.engappai.2024.108087
[25]	W. Zhang, G. Peng, C. Li, Y. Chen, Z. Zhang, A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals, Sensors, 17 (2017). https://doi.org/10.3390/s17020425 doi: 10.3390/s17020425
[26]	Q. Wang, F. Xu, A novel rolling bearing fault diagnosis method based on adaptive denoising convolutional neural network under noise background, Measurement, 218 (2023) 113209. https://doi.org/10.1016/j.measurement.2023.113209 doi: 10.1016/j.measurement.2023.113209
[27]	Z. Niu, G. Zhong, H. Yu, A review on the attention mechanism of deep learning, Neurocomputing, 452 (2021) 48–62. https://doi.org/10.1016/j.neucom.2021.03.091 doi: 10.1016/j.neucom.2021.03.091
[28]	K. Zhang, B. Tang, L. Deng, X. Liu, A hybrid attention improved ResNet based fault diagnosis method of wind turbines gearbox, Measurement, 179 (2021), 109491. https://doi.org/10.1016/j.measurement.2021.109491 doi: 10.1016/j.measurement.2021.109491
[29]	Q. Snyder, Q. Jiang, E. Tripp, Integrating self-attention mechanisms in deep learning: A novel dual-head ensemble transformer with its application to bearing fault diagnosis, Signal Process. , 227 (2025), 109683. https://doi.org/10.1016/j.sigpro.2024.109683 doi: 10.1016/j.sigpro.2024.109683
[30]	J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in 2018 IEEE /CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2018), 7132–7141. https://doi.org/10.48550/arXiv.1709.01507
[31]	Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, Q. Hu, ECA-Net: Efficient channel attention for deep convolutional neural networks, in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2020), 11531–11539. https://doi.org/10.48550/arXiv.1910.03151
[32]	Z. Gao, J. Xie, Q. Wang, P. Li, Global second-order pooling convolutional networks, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2019), 3019–3028. https://doi.org/10.1109/CVPR.2019.00314
[33]	Z. Qin, P. Zhang, F. Wu, X. Li, FcaNet: Frequency channel attention networks, in 2021 IEEE/CVF International Conference on Computer Vision (ICCV), (2021), 763–772. https://doi.org/10.1109/ICCV48922.2021.00082
[34]	M. Zhao, S. Zhong, X. Fu, B. Tang, M. Pecht, Deep residual shrinkage networks for fault diagnosis, IEEE Trans. Ind. Inf. , 16 (2020), 4681–4690. https://doi.org/10.1109/TII.2019.2943898 doi: 10.1109/TII.2019.2943898
[35]	M. Zhao, S. Zhong, X. Fu, B. Tang, S. Dong, M. Pecht, Deep residual networks with adaptively parametric rectifier linear units for fault diagnosis, IEEE Trans. Ind. Electron. , 68 (2021), 2587–2597. https://doi.org/10.1109/TIE.2020.2972458 doi: 10.1109/TIE.2020.2972458
[36]	M. Nagubandi, R. Walia, A. Karanath, G. N. Pillai, Electric load forecasting using dual-stage attention network with cosine annealed warm restart schedule, in 2022 International Conference on Emerging Techniques in Computational Intelligence (ICETCI), (2022), 141–146. https://doi.org/10.1109/ICETCI55171.2022.9921361
[37]	P. T. De Boer, D. P. Kroese, S. Mannor, R. Y. Rubinstein, A tutorial on the cross-entropy method, Ann. Oper. Res. , 134 (2005), 19–67. https://doi.org/10.1007/s10479-005-5724-z doi: 10.1007/s10479-005-5724-z
[38]	W. A. Smith, R. B. Randall, Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study, Mech. Syst. Signal Process. , 64 (2015), 100–131. https://doi.org/10.1016/j.ymssp.2015.04.021 doi: 10.1016/j.ymssp.2015.04.021
[39]	Y. Wang, P. W. Tse, B. Tang, Y. Qin, L. Deng, T. Huang, Kurtogram manifold learning and its application to rolling bearing weak signal detection, Measurement, 127 (2018), 533–545. https://doi.org/10.1016/j.measurement.2018.06.026 doi: 10.1016/j.measurement.2018.06.026
[40]	P. Rodríguez, M. A. Bautista, J. Gonzàlez, S. Escalera, Beyond one-hot encoding: Lower dimensional target embedding, Image Vision Comput. , 75 (2018), 21–31. https://doi.org/10.1016/j.imavis.2018.04.004 doi: 10.1016/j.imavis.2018.04.004
[41]	L. Maaten, G. Hinton, Visualizing data using t-SNE, J. Mach. Learn. Res. , 9 (2008), 2579–2605.
[42]	S. Shao, S. McAleer, R. Yan, P. Baldi, Highly accurate machine fault diagnosis using deep transfer learning, IEEE Trans. Ind. Inf. , 15 (2018), 2446–2455. https://doi.org/10.1109/TII.2018.2864759 doi: 10.1109/TII.2018.2864759

Reader Comments

Your name:*

Email:*
© 2025 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)