An Enhanced Lightweight Multi-scale CNN with Resonance-dominant Frequency-band Learning for Robust Bearing Fault Diagnosis
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Published
Nov 7, 2026
Thanh Tung Luu
Duy An Huynh
Thanh Hai Nguyen
Abstract
Rolling bearings are essential components in rotating machinery, and reliable early fault detection is crucial for avoiding unexpected failures and reducing maintenance costs. While deep learning techniques have achieved notable progress, most prior studies have emphasized feature enrichment without thoroughly examining vibration spectral characteristics or establishing mechanisms to select the most informative time–frequency patterns. To exploit this physical insight, this study proposes an enhanced lightweight multi-scale convolutional neural network (CNN) with adaptive frequency-band learning for robust bearing fault diagnosis. Vibration signals are first band-limited to the resonance-dominant range and transformed using the Continuous Wavelet Transform with the Morlet wavelet, improving signal-to-noise ratio while preserving impulsive fault components. The proposed architecture integrates depthwise separable convolutions, multi-scale parallel branches, Squeeze-and-Excitation channel recalibration, and Atrous Spatial Pyramid Pooling to capture discriminative resonance-sensitive features with reduced computational complexity. Grad-CAM is employed to visualize the resonance bands contributing to classification decisions. Experiments on the CWRU dataset achieve accuracy above 99% with only 7.69 M parameters. Robustness under additive noise and cross-domain validation on the HUST dataset confirm strong generalization and domain invariance.
##plugins.themes.bootstrap3.article.details##
Keywords
Rolling bearing, Pattern recognition, Fault diagnosis, Multi-scale convolution, Enhanced lightweight model
References
Chen, Z., Cen, J., & Xiong, J. (2020). Rolling bearing fault diagnosis using time-frequency analysis and deep transfer convolutional neural network. IEEE Access, 8, 150248–150261.
Zheng, Z., Fu, J., Lu, C., & Zhu, Y. (2021). Research on rolling bearing fault diagnosis of small dataset based on a new optimal transfer learning network. Measurement, 177, 109285.
Randall, R.B., & Antoni, J. (2011). Rolling element bearing diagnostics — A tutorial. Mechanical Systems and Signal Processing, 25(2), 485–520.
Lei, Y., Lin, J., He, Z., & Zuo, M.J. (2013). A review on empirical mode decomposition in fault diagnosis of rotating machinery. Mechanical Systems and Signal Processing, 35(1–2), 108–126.
Widodo, A., & Yang, B.S. (2007). Support vector machine in machine condition monitoring and fault diagnosis. Mechanical Systems and Signal Processing, 21(6), 2560–2574.
Cerrada, M., et al. (2016). Fault diagnosis in spur gears based on genetic algorithm and random forest. Mechanical Systems and Signal Processing, 70–71, 87–103.
Zhao, R., et al. (2019). Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing, 115, 213–237.
Chen, Z., et al. (2022). A transformer-based fault diagnosis approach for rotating machinery. IEEE Transactions on Industrial Informatics, 18(6), 4086–4096
Eren, L., Ince, T., & Kiranyaz, S. (2019). A generic intelligent bearing fault diagnosis system using compact adaptive 1D CNN classifier. Journal of Signal Processing Systems, 91(2), 179–189.
Zhang, W., Li, C., Peng, G., Chen, Y., & Zhang, Z. (2018). A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load. Mechanical Systems and Signal Processing, 100, 439–453.
Toma, R. N., et al. (2022). A bearing fault classification framework based on image encoding techniques and a convolutional neural network under different operating conditions. Sensors, 22(13), 4881.
Wang, B., Feng, G., Huo, D., & Kang, Y. (2022). A bearing fault diagnosis method based on spectrum map information fusion and convolutional neural network. Processes, 10(7), 1426.
Deveci, B. U., et al. (2024). Transfer learning enabled bearing fault detection methods based on image representations of single-dimensional signals. Information Systems Frontiers, 26, 1345–1397.
Jia, F., Lei, Y., Lin, J., Zhou, X., & Lu, N. (2016). Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mechanical Systems and Signal Processing, 72, 303–315.
Zhao, R., Zhang, C., & Xue, D. (2024). A multi-scale multi-channel CNN introducing a channel-spatial attention mechanism for hyperspectral remote sensing image classification. European Journal of Remote Sensing, 57(1), 1–14.
Wang, X., Hua, T., Xu, S., & Zhao, X. (2023). A novel rolling bearing fault diagnosis method based on BLS and CNN with attention mechanism. Machines, 11(2), 279.
Zhou, J., Ma, R., & Chen, J. (2022, January). Bearing fault diagnosis based on 1D-CNN-LSTM-TL. In 7th International Conference on Electronic Technology and Information Science (ICETIS) (pp. 1–6). IEEE.
Rabah, A., & Abdelhafid, K. (2018). Rolling bearing fault diagnosis based on improved complete ensemble empirical mode decomposition with adaptive noise combined with minimum entropy deconvolution. Journal of Vibroengineering, 20(1), 240–257.
Liang, H., Cao, J., & Zhao, X. (2022). Multi-scale dynamic adaptive residual network for fault diagnosis. Measurement, 188, 110397.
Liang, Y.-P., Chen, H., & Chung, C.-C. (2024). A One-Dimensional Depthwise Separable Convolutional Neural Network for Bearing Fault Diagnosis Implemented on FPGA. Sensors, 24(23), 7831.
H. Xu, Y. Xiao, K. Sun and L. Cui, "Improved Depthwise Separable Convolution for Transfer Learning in Fault Diagnosis," in IEEE Sensors Journal, vol. 24, no. 20, pp. 33606-33613, 15 Oct. 2024, doi:
Wu, Y., Dai, J., Yang, X., Shao, F., Gong, J., Zhang, P., & Liu, S. (2025). The Fault Diagnosis of Rolling Bearings Based on FFT-SE-TCN-SVM. Actuators, 14(3), 152.
Gu, X., Tian, Y., Li, C., Wei, Y., & Li, D. (2024). Improved SE-ResNet Acoustic–Vibration Fusion for Rolling Bearing Composite Fault Diagnosis. Applied Sciences, 14(5), 2182.
Wang, Q., Yin, C., She, K., Tong, Q., Lu, G., Zhang, H., & Lu, J. (2025). Bearing fault diagnosis for variable operating conditions based on KAN convolution and dual branch fusion attention. Scientific Reports, 15(1), 21442.
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision (pp. 618–626).
Jiang, K., Yang, Z., Jin, T., Chen, C., Liu, Z., & Zhang, B. (2025). CNN-based rolling bearing fault diagnosis method with quantifiable interpretability. IEEE Transactions on Instrumentation and Measurement.
Aziz, S.; Khan, M.U.; Usman, A.; Faraz, M.; Ghadi, Y.Y.; Montes, G.A. Bearing faults classification using novel log energy-based empirical mode decomposition and machine Mel-frequency cepstral coefficients. Digit. Signal Process. 2025, 156, 104776.
Liefstingh, M., Taal, C., Restrepo, S. E., & Azarfar, A. (2021, November). Interpretation of deep learning models in bearing fault diagnosis. Annual Conference of the PHM Society, 13(1).
Peng, Z. K., & Chu, F. L. (2004). Application of the wavelet transform in machine condition monitoring and fault diagnostics: A review with bibliography. Mechanical Systems and Signal Processing, 18(2), 199–221.
Huang, K., Zhu, L., Ren, Z., Lin, T., Zeng, L., Wan, J., & Zhu, Y. (2024). An improved fault diagnosis method for rolling bearings based on 1D_CNN considering noise and working condition interference. Machines, 12(6), 383.
Pandhare, V., Singh, J., & Lee, J. (2019, May). Convolutional neural network based rolling-element bearing fault diagnosis for naturally occurring and progressing defects using time-frequency domain features. In 2019 Prognostics and System Health Management Conference (PHM-Paris) (pp. 320–326). IEEE.
Li, L., Zhao, X., Liu, X., & Fei, J. (2022, June). Rolling bearing fault diagnosis based on convolutional neural network and multi-sensor information fusion. In 2022 IEEE 10th Joint International Information Technology and Artificial Intelligence Conference (ITAIC) (Vol. 10, pp. 1396–1401). IEEE.
Liao, S., Wu, Y., & Wu, Y. (2022). Bearing fault diagnosis using a Grad-CAM-based convolutional neuro-fuzzy network. Mathematics, 10(13), 2075.
Petrosian, O., Pengyi, L., Yulong, H., Jiarui, L., Zhaoruikun, S., Guofeng, F., & Liping, M. (2024). DKDL-Net: A lightweight bearing fault detection model via decoupled knowledge distillation and low-rank adaptation fine-tuning. IEEE Transactions on Industrial Informatics, 20(3), 4567–4578.
Yu, B., Li, S., & Liu, J. (2023). Fault diagnosis of printing press bearing based on deformable convolutional ResNet. AIMS Mathematics, 8(3), 5273–5291.
Liu, H., Zhang, F., Tan, Y., Huang, L., Li, Y., Huang, G., Luo, S., & Zeng, A. (2024). Multi-scale quaternion CNN and BiGRU with cross self-attention feature fusion for fault diagnosis of bearing. Measurement Science and Technology, 35(8), 086138.
Yao, C., Zhou, L., & Jiang, W. (2023). Lite and efficient deep learning model for bearing fault diagnosis using the CWRU dataset. Sensors, 23(6), 3157.
Khan, M. A., Asad, B., Kudelina, K., Vaimann, T., & Kallaste, A. (2022). The bearing faults detection methods for electrical machines—the state of the art. Energies, 16(1), 296.
Thuan, N.D.; Hong, H.S. HUST bearing: A practical dataset for ball bearing fault diagnosis. BMC Res. Notes 2023, 16, 138.
Zheng, Z., Fu, J., Lu, C., & Zhu, Y. (2021). Research on rolling bearing fault diagnosis of small dataset based on a new optimal transfer learning network. Measurement, 177, 109285.
Randall, R.B., & Antoni, J. (2011). Rolling element bearing diagnostics — A tutorial. Mechanical Systems and Signal Processing, 25(2), 485–520.
Lei, Y., Lin, J., He, Z., & Zuo, M.J. (2013). A review on empirical mode decomposition in fault diagnosis of rotating machinery. Mechanical Systems and Signal Processing, 35(1–2), 108–126.
Widodo, A., & Yang, B.S. (2007). Support vector machine in machine condition monitoring and fault diagnosis. Mechanical Systems and Signal Processing, 21(6), 2560–2574.
Cerrada, M., et al. (2016). Fault diagnosis in spur gears based on genetic algorithm and random forest. Mechanical Systems and Signal Processing, 70–71, 87–103.
Zhao, R., et al. (2019). Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing, 115, 213–237.
Chen, Z., et al. (2022). A transformer-based fault diagnosis approach for rotating machinery. IEEE Transactions on Industrial Informatics, 18(6), 4086–4096
Eren, L., Ince, T., & Kiranyaz, S. (2019). A generic intelligent bearing fault diagnosis system using compact adaptive 1D CNN classifier. Journal of Signal Processing Systems, 91(2), 179–189.
Zhang, W., Li, C., Peng, G., Chen, Y., & Zhang, Z. (2018). A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load. Mechanical Systems and Signal Processing, 100, 439–453.
Toma, R. N., et al. (2022). A bearing fault classification framework based on image encoding techniques and a convolutional neural network under different operating conditions. Sensors, 22(13), 4881.
Wang, B., Feng, G., Huo, D., & Kang, Y. (2022). A bearing fault diagnosis method based on spectrum map information fusion and convolutional neural network. Processes, 10(7), 1426.
Deveci, B. U., et al. (2024). Transfer learning enabled bearing fault detection methods based on image representations of single-dimensional signals. Information Systems Frontiers, 26, 1345–1397.
Jia, F., Lei, Y., Lin, J., Zhou, X., & Lu, N. (2016). Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mechanical Systems and Signal Processing, 72, 303–315.
Zhao, R., Zhang, C., & Xue, D. (2024). A multi-scale multi-channel CNN introducing a channel-spatial attention mechanism for hyperspectral remote sensing image classification. European Journal of Remote Sensing, 57(1), 1–14.
Wang, X., Hua, T., Xu, S., & Zhao, X. (2023). A novel rolling bearing fault diagnosis method based on BLS and CNN with attention mechanism. Machines, 11(2), 279.
Zhou, J., Ma, R., & Chen, J. (2022, January). Bearing fault diagnosis based on 1D-CNN-LSTM-TL. In 7th International Conference on Electronic Technology and Information Science (ICETIS) (pp. 1–6). IEEE.
Rabah, A., & Abdelhafid, K. (2018). Rolling bearing fault diagnosis based on improved complete ensemble empirical mode decomposition with adaptive noise combined with minimum entropy deconvolution. Journal of Vibroengineering, 20(1), 240–257.
Liang, H., Cao, J., & Zhao, X. (2022). Multi-scale dynamic adaptive residual network for fault diagnosis. Measurement, 188, 110397.
Liang, Y.-P., Chen, H., & Chung, C.-C. (2024). A One-Dimensional Depthwise Separable Convolutional Neural Network for Bearing Fault Diagnosis Implemented on FPGA. Sensors, 24(23), 7831.
H. Xu, Y. Xiao, K. Sun and L. Cui, "Improved Depthwise Separable Convolution for Transfer Learning in Fault Diagnosis," in IEEE Sensors Journal, vol. 24, no. 20, pp. 33606-33613, 15 Oct. 2024, doi:
Wu, Y., Dai, J., Yang, X., Shao, F., Gong, J., Zhang, P., & Liu, S. (2025). The Fault Diagnosis of Rolling Bearings Based on FFT-SE-TCN-SVM. Actuators, 14(3), 152.
Gu, X., Tian, Y., Li, C., Wei, Y., & Li, D. (2024). Improved SE-ResNet Acoustic–Vibration Fusion for Rolling Bearing Composite Fault Diagnosis. Applied Sciences, 14(5), 2182.
Wang, Q., Yin, C., She, K., Tong, Q., Lu, G., Zhang, H., & Lu, J. (2025). Bearing fault diagnosis for variable operating conditions based on KAN convolution and dual branch fusion attention. Scientific Reports, 15(1), 21442.
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision (pp. 618–626).
Jiang, K., Yang, Z., Jin, T., Chen, C., Liu, Z., & Zhang, B. (2025). CNN-based rolling bearing fault diagnosis method with quantifiable interpretability. IEEE Transactions on Instrumentation and Measurement.
Aziz, S.; Khan, M.U.; Usman, A.; Faraz, M.; Ghadi, Y.Y.; Montes, G.A. Bearing faults classification using novel log energy-based empirical mode decomposition and machine Mel-frequency cepstral coefficients. Digit. Signal Process. 2025, 156, 104776.
Liefstingh, M., Taal, C., Restrepo, S. E., & Azarfar, A. (2021, November). Interpretation of deep learning models in bearing fault diagnosis. Annual Conference of the PHM Society, 13(1).
Peng, Z. K., & Chu, F. L. (2004). Application of the wavelet transform in machine condition monitoring and fault diagnostics: A review with bibliography. Mechanical Systems and Signal Processing, 18(2), 199–221.
Huang, K., Zhu, L., Ren, Z., Lin, T., Zeng, L., Wan, J., & Zhu, Y. (2024). An improved fault diagnosis method for rolling bearings based on 1D_CNN considering noise and working condition interference. Machines, 12(6), 383.
Pandhare, V., Singh, J., & Lee, J. (2019, May). Convolutional neural network based rolling-element bearing fault diagnosis for naturally occurring and progressing defects using time-frequency domain features. In 2019 Prognostics and System Health Management Conference (PHM-Paris) (pp. 320–326). IEEE.
Li, L., Zhao, X., Liu, X., & Fei, J. (2022, June). Rolling bearing fault diagnosis based on convolutional neural network and multi-sensor information fusion. In 2022 IEEE 10th Joint International Information Technology and Artificial Intelligence Conference (ITAIC) (Vol. 10, pp. 1396–1401). IEEE.
Liao, S., Wu, Y., & Wu, Y. (2022). Bearing fault diagnosis using a Grad-CAM-based convolutional neuro-fuzzy network. Mathematics, 10(13), 2075.
Petrosian, O., Pengyi, L., Yulong, H., Jiarui, L., Zhaoruikun, S., Guofeng, F., & Liping, M. (2024). DKDL-Net: A lightweight bearing fault detection model via decoupled knowledge distillation and low-rank adaptation fine-tuning. IEEE Transactions on Industrial Informatics, 20(3), 4567–4578.
Yu, B., Li, S., & Liu, J. (2023). Fault diagnosis of printing press bearing based on deformable convolutional ResNet. AIMS Mathematics, 8(3), 5273–5291.
Liu, H., Zhang, F., Tan, Y., Huang, L., Li, Y., Huang, G., Luo, S., & Zeng, A. (2024). Multi-scale quaternion CNN and BiGRU with cross self-attention feature fusion for fault diagnosis of bearing. Measurement Science and Technology, 35(8), 086138.
Yao, C., Zhou, L., & Jiang, W. (2023). Lite and efficient deep learning model for bearing fault diagnosis using the CWRU dataset. Sensors, 23(6), 3157.
Khan, M. A., Asad, B., Kudelina, K., Vaimann, T., & Kallaste, A. (2022). The bearing faults detection methods for electrical machines—the state of the art. Energies, 16(1), 296.
Thuan, N.D.; Hong, H.S. HUST bearing: A practical dataset for ball bearing fault diagnosis. BMC Res. Notes 2023, 16, 138.
Section
Technical Papers