WANG, Teng ;TANG, Youfu ;WANG, Tao ;LEI, Na . An Improved MSCNN and GRU Model for Rolling Bearing Fault Diagnosis. Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 69, n.5-6, p. 261-274, february 2023. ISSN 0039-2480. Available at: <https://www.sv-jme.eu/sl/article/based-on-the-improved-mscnn-and-gru-model-for-rolling-bearing-fault-diagnosis/>. Date accessed: 21 dec. 2024. doi:http://dx.doi.org/10.5545/sv-jme.2022.459.
Wang, T., Tang, Y., Wang, T., & Lei, N. (2023). An Improved MSCNN and GRU Model for Rolling Bearing Fault Diagnosis. Strojniški vestnik - Journal of Mechanical Engineering, 69(5-6), 261-274. doi:http://dx.doi.org/10.5545/sv-jme.2022.459
@article{sv-jmesv-jme.2022.459,
author = {Teng Wang and Youfu Tang and Tao Wang and Na Lei},
title = {An Improved MSCNN and GRU Model for Rolling Bearing Fault Diagnosis},
journal = {Strojniški vestnik - Journal of Mechanical Engineering},
volume = {69},
number = {5-6},
year = {2023},
keywords = {SENet; multiscale convolutional neural networks; gate recurrent unit; rolling bearing; fault diagnosis; },
abstract = {In this paper, a novel fault diagnosis method based on the fusion of squeeze and excitation-multiscale convolutional neural networks (SENet-MSCNN) and gate recurrent unit (GRU) is proposed to address the problem of low diagnosis rate caused by the fact that normal samples are much larger than fault samples in the vibration big data. The method takes the time-domain vibration signal as input and fuses the spatial features extracted by SENet-MSCNN. The temporal features extracted by GRU in order to bring them into the fully connected layer for identification so as to realize the intelligent diagnosis of rolling bearing adaptive feature extraction. Finally, the method is applied to the simulated signal and experimental data for testing and analysis. The results reveal that the model can reach 98.98 % and 76.44 % migration diagnostic accuracy in bearing and gearbox datasets. At the same time, it has strong noise immunity, adaptivity, and robustness, providing an effective way for intelligent diagnosis of rolling bearing vibration big data.},
issn = {0039-2480}, pages = {261-274}, doi = {10.5545/sv-jme.2022.459},
url = {https://www.sv-jme.eu/sl/article/based-on-the-improved-mscnn-and-gru-model-for-rolling-bearing-fault-diagnosis/}
}
Wang, T.,Tang, Y.,Wang, T.,Lei, N. 2023 February 69. An Improved MSCNN and GRU Model for Rolling Bearing Fault Diagnosis. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 69:5-6
%A Wang, Teng %A Tang, Youfu %A Wang, Tao %A Lei, Na %D 2023 %T An Improved MSCNN and GRU Model for Rolling Bearing Fault Diagnosis %B 2023 %9 SENet; multiscale convolutional neural networks; gate recurrent unit; rolling bearing; fault diagnosis; %! An Improved MSCNN and GRU Model for Rolling Bearing Fault Diagnosis %K SENet; multiscale convolutional neural networks; gate recurrent unit; rolling bearing; fault diagnosis; %X In this paper, a novel fault diagnosis method based on the fusion of squeeze and excitation-multiscale convolutional neural networks (SENet-MSCNN) and gate recurrent unit (GRU) is proposed to address the problem of low diagnosis rate caused by the fact that normal samples are much larger than fault samples in the vibration big data. The method takes the time-domain vibration signal as input and fuses the spatial features extracted by SENet-MSCNN. The temporal features extracted by GRU in order to bring them into the fully connected layer for identification so as to realize the intelligent diagnosis of rolling bearing adaptive feature extraction. Finally, the method is applied to the simulated signal and experimental data for testing and analysis. The results reveal that the model can reach 98.98 % and 76.44 % migration diagnostic accuracy in bearing and gearbox datasets. At the same time, it has strong noise immunity, adaptivity, and robustness, providing an effective way for intelligent diagnosis of rolling bearing vibration big data. %U https://www.sv-jme.eu/sl/article/based-on-the-improved-mscnn-and-gru-model-for-rolling-bearing-fault-diagnosis/ %0 Journal Article %R 10.5545/sv-jme.2022.459 %& 261 %P 14 %J Strojniški vestnik - Journal of Mechanical Engineering %V 69 %N 5-6 %@ 0039-2480 %8 2023-02-28 %7 2023-02-28
Wang, Teng, Youfu Tang, Tao Wang, & Na Lei. "An Improved MSCNN and GRU Model for Rolling Bearing Fault Diagnosis." Strojniški vestnik - Journal of Mechanical Engineering [Online], 69.5-6 (2023): 261-274. Web. 21 Dec. 2024
TY - JOUR AU - Wang, Teng AU - Tang, Youfu AU - Wang, Tao AU - Lei, Na PY - 2023 TI - An Improved MSCNN and GRU Model for Rolling Bearing Fault Diagnosis JF - Strojniški vestnik - Journal of Mechanical Engineering DO - 10.5545/sv-jme.2022.459 KW - SENet; multiscale convolutional neural networks; gate recurrent unit; rolling bearing; fault diagnosis; N2 - In this paper, a novel fault diagnosis method based on the fusion of squeeze and excitation-multiscale convolutional neural networks (SENet-MSCNN) and gate recurrent unit (GRU) is proposed to address the problem of low diagnosis rate caused by the fact that normal samples are much larger than fault samples in the vibration big data. The method takes the time-domain vibration signal as input and fuses the spatial features extracted by SENet-MSCNN. The temporal features extracted by GRU in order to bring them into the fully connected layer for identification so as to realize the intelligent diagnosis of rolling bearing adaptive feature extraction. Finally, the method is applied to the simulated signal and experimental data for testing and analysis. The results reveal that the model can reach 98.98 % and 76.44 % migration diagnostic accuracy in bearing and gearbox datasets. At the same time, it has strong noise immunity, adaptivity, and robustness, providing an effective way for intelligent diagnosis of rolling bearing vibration big data. UR - https://www.sv-jme.eu/sl/article/based-on-the-improved-mscnn-and-gru-model-for-rolling-bearing-fault-diagnosis/
@article{{sv-jme}{sv-jme.2022.459},
author = {Wang, T., Tang, Y., Wang, T., Lei, N.},
title = {An Improved MSCNN and GRU Model for Rolling Bearing Fault Diagnosis},
journal = {Strojniški vestnik - Journal of Mechanical Engineering},
volume = {69},
number = {5-6},
year = {2023},
doi = {10.5545/sv-jme.2022.459},
url = {https://www.sv-jme.eu/sl/article/based-on-the-improved-mscnn-and-gru-model-for-rolling-bearing-fault-diagnosis/}
}
TY - JOUR AU - Wang, Teng AU - Tang, Youfu AU - Wang, Tao AU - Lei, Na PY - 2023/02/28 TI - An Improved MSCNN and GRU Model for Rolling Bearing Fault Diagnosis JF - Strojniški vestnik - Journal of Mechanical Engineering; Vol 69, No 5-6 (2023): Strojniški vestnik - Journal of Mechanical Engineering DO - 10.5545/sv-jme.2022.459 KW - SENet, multiscale convolutional neural networks, gate recurrent unit, rolling bearing, fault diagnosis, N2 - In this paper, a novel fault diagnosis method based on the fusion of squeeze and excitation-multiscale convolutional neural networks (SENet-MSCNN) and gate recurrent unit (GRU) is proposed to address the problem of low diagnosis rate caused by the fact that normal samples are much larger than fault samples in the vibration big data. The method takes the time-domain vibration signal as input and fuses the spatial features extracted by SENet-MSCNN. The temporal features extracted by GRU in order to bring them into the fully connected layer for identification so as to realize the intelligent diagnosis of rolling bearing adaptive feature extraction. Finally, the method is applied to the simulated signal and experimental data for testing and analysis. The results reveal that the model can reach 98.98 % and 76.44 % migration diagnostic accuracy in bearing and gearbox datasets. At the same time, it has strong noise immunity, adaptivity, and robustness, providing an effective way for intelligent diagnosis of rolling bearing vibration big data. UR - https://www.sv-jme.eu/sl/article/based-on-the-improved-mscnn-and-gru-model-for-rolling-bearing-fault-diagnosis/
Wang, Teng, Tang, Youfu, Wang, Tao, AND Lei, Na. "An Improved MSCNN and GRU Model for Rolling Bearing Fault Diagnosis" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 69 Number 5-6 (28 February 2023)
Strojniški vestnik - Journal of Mechanical Engineering 69(2023)5-6, 261-274
© The Authors 2023. CC BY 4.0 Int.
In this paper, a novel fault diagnosis method based on the fusion of squeeze and excitation-multiscale convolutional neural networks (SENet-MSCNN) and gate recurrent unit (GRU) is proposed to address the problem of low diagnosis rate caused by the fact that normal samples are much larger than fault samples in the vibration big data. The method takes the time-domain vibration signal as input and fuses the spatial features extracted by SENet-MSCNN. The temporal features extracted by GRU in order to bring them into the fully connected layer for identification so as to realize the intelligent diagnosis of rolling bearing adaptive feature extraction. Finally, the method is applied to the simulated signal and experimental data for testing and analysis. The results reveal that the model can reach 98.98 % and 76.44 % migration diagnostic accuracy in bearing and gearbox datasets. At the same time, it has strong noise immunity, adaptivity, and robustness, providing an effective way for intelligent diagnosis of rolling bearing vibration big data.