Efficient Method for Gearbox Fault Diagnosis Under Variable Speed Conditions Using WVD Based Time Frequency Information of Vibration Signals and Deep Learning
Raied Qaied Ajmi
Department of Mechanical Engineering, Babylon Technical Institute, Al-Furat Al-Awsat Technical University, Najaf, Iraq.
The gearbox fault diagnosis under variable speed remains one of key challenges in industrial domain due to the nonlinear and time-varying nature of vibration measurements. In this paper, a highly-efficient hybrid method that combines the Wigner-Ville Distribution (WVD) based time-frequency representation and deep learning model to improve the accuracy of fault detection is suggested. WVD converts the signals of vibration to rich time-frequency representations in which complex fault-based patterns are recorded. We use an Attention-Based Convolutional Neural Network (Attention-CNN) to be able to extract useful features out of these representations, with _attention_ giving priority to the most pertinent areas. The features so extracted are further fed to an effective Random Forest (RF) model, and this effectiveness minimizes overfitting and maximizes the generalizability even across the changing speed settings. A comparative analysis of the proposed model is performed with vibration data of a publicly available gearbox fault dataset, which is outperforming the traditional techniques. The results show that the method is expecting 99.73 per cent accuracy, higher than the available methods of machine and deep learning. In addition to the above, a flexible measurement procedure is proposed to examine the fault diagnosis reliability under various loads to verify robustness in a real-life condition. The results support the fact that the suggested approach can enhance the gearbox condition monitoring and predictive maintenance approaches.
Keywords
Gearbox Fault Diagnosis, WVD-Based Time–Frequency, Vibration Signals, Deep Learning.
S. Suryawanshi, S. Gavali, V. Darwai, S. Patil, A. Wankhede, and A. Borse, “Gearbox Fault Diagnosis: A Comparative Study of Machine Learning and Deep Learning Approaches,” Inventive Communication and Computational Technologies, pp. 335–349, 2024, doi: 10.1007/978-981-97-7710-5_25.
N. S K, S. K. Ramalinge Gowda, Rayappa Shrinivas Mahale, and A. Patil, “A Review on Gearbox Condition Monitoring and Signal Analysis Techniques,” Scientific Hypotheses, vol. 1, pp. 36–46, Apr. 2024, doi: 10.69530/15vwy749.
Y. Guo, S. Jiang, Y. Yang, X. Jin, and Y. Wei, “Gearbox Fault Diagnosis Based on Improved Variational Mode Extraction,” Sensors, vol. 22, no. 5, p. 1779, Feb. 2022, doi: 10.3390/s22051779.
W. Wen, Y. Bai, and W. Cheng, “Generative Adversarial Learning Enhanced Fault Diagnosis for Planetary Gearbox under Varying Working Conditions,” Sensors, vol. 20, no. 6, p. 1685, Mar. 2020, doi: 10.3390/s20061685.
Q. Xu, H. Jiang, X. Zhang, J. Li, and L. Chen, “Multiscale Convolutional Neural Network Based on Channel Space Attention for Gearbox Compound Fault Diagnosis,” Sensors, vol. 23, no. 8, p. 3827, Apr. 2023, doi: 10.3390/s23083827.
S. Chen, Z. Liu, X. He, D. Zou, and D. Zhou, “Multi-mode fault diagnosis datasets of gearbox under variable working conditions,” Data in Brief, vol. 54, p. 110453, Jun. 2024, doi: 10.1016/j.dib.2024.110453.
X. Wang, Y. Du, and X. Ji, “Gearbox Fault Diagnosis Based on Adaptive Variational Mode Decomposition–Stationary Wavelet Transform and Ensemble Refined Composite Multiscale Fluctuation Dispersion Entropy,” Sensors, vol. 24, no. 22, p. 7129, Nov. 2024, doi: 10.3390/s24227129.
J.-D. Wu, W.-J. Luo, and K.-C. Yao, “Electric Motor Vibration Signal Classification Using Wigner–Ville Distribution for Fault Diagnosis,” Sensors, vol. 25, no. 4, p. 1196, Feb. 2025, doi: 10.3390/s25041196.
D. Aiordăchioaie, “A comparative analysis of fault detection and process diagnosis methods based on a signal processing paradigm,” Discover Applied Sciences, vol. 7, no. 1, Dec. 2024, doi: 10.1007/s42452-024-06390-3.
M. Bessaoudi, H. Habbouche, T. Benkedjouh, and A. Mesloub, “A hybrid approach for gearbox fault diagnosis based on deep learning techniques,” The International Journal of Advanced Manufacturing Technology, vol. 133, no. 5–6, pp. 2861–2874, Jun. 2024, doi: 10.1007/s00170-024-13873-5.
I. Lupea and M. Lupea, “Continuous Wavelet Transform and CNN for Fault Detection in a Helical Gearbox,” Applied Sciences, vol. 15, no. 2, p. 950, Jan. 2025, doi: 10.3390/app15020950.
Afia A, Gougam F, Rahmoune C, Touzout W, Ouelmokhtar H, Benazzouz D. Gearbox fault diagnosis using remd, eo and machine learning classifiers. J Vib Eng Technol. 2024;12(3):4673-97. DOI: 10.1007/s42417-023-00613-4.
H. Song, Y. Sun, H. Gao, L. Guo, and Y. Chen, “Multibranch Time-Frequency Spectrum Segmentation Approach for Gearbox Fault Diagnosis,” IEEE Sensors Journal, vol. 24, no. 22, pp. 38155–38164, Nov. 2024, doi: 10.1109/jsen.2024.3457878.
L. Wang, Z. Zhang, H. Long, J. Xu, and R. Liu, “Wind Turbine Gearbox Failure Identification With Deep Neural Networks,” IEEE Transactions on Industrial Informatics, vol. 13, no. 3, pp. 1360–1368, Jun. 2017, doi: 10.1109/tii.2016.2607179.
Z. Yuan, M. Qiao, and C. Xu, “Gear Fault Diagnosis Using the WSET-CNN-BKA-LSSVM Method,” 2024 5th International Conference on Electronic Communication and Artificial Intelligence (ICECAI), pp. 282–286, May 2024, doi: 10.1109/icecai62591.2024.10675198.
Y. Dong, H. Jiang, X. Wang, M. Mu, and W. Jiang, “An interpretable multiscale lifting wavelet contrast network for planetary gearbox fault diagnosis with small samples,” Reliability Engineering & System Safety, vol. 251, p. 110404, Nov. 2024, doi: 10.1016/j.ress.2024.110404.
X. Zheng, R. Hao, H. Sun, B. Yao, T. Shang, and T. Wang, “Gearbox Fault Diagnosis Based on MTF-ECA-ResNeXt,” 2024 IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC), vol. 37, pp. 295–300, Jul. 2024, doi: 10.1109/sdpc62810.2024.10707726.
H. Gong, X. Nie, and G. Xie, “Research on Gearbox Fault Diagnosis Method Based on ECA Improved VGG16,” 2024 43rd Chinese Control Conference (CCC), pp. 4996–5001, Jul. 2024, doi: 10.23919/ccc63176.2024.10662349.
I. Ahmed, M. Ahmad, A. Chehri, and G. Jeon, “A Smart-Anomaly-Detection System for Industrial Machines Based on Feature Autoencoder and Deep Learning,” Micromachines, vol. 14, no. 1, p. 154, Jan. 2023, doi: 10.3390/mi14010154.
S. Arshad Mayo, S. Rehman, and Z. Cai, “High-accuracy gearbox fault detection using deep learning on vibrational data,” Journal of Physics: Conference Series, vol. 2853, no. 1, p. 012066, Oct. 2024, doi: 10.1088/1742-6596/2853/1/012066.
J. van den Hoogen, D. Hudson, S. Bloemheuvel, and M. Atzmueller, “Hyperparameter analysis of wide-kernel CNN architectures in industrial fault detection: an exploratory study,” International Journal of Data Science and Analytics, vol. 18, no. 4, pp. 423–444, Sep. 2023, doi: 10.1007/s41060-023-00440-6.
Y. Byun, D. Maeng, and J.-G. Baek, “Unsupervised fault detection using frequency-wise angular filtering in contaminated vibration signals,” International Journal of Production Research, vol. 63, no. 10, pp. 3733–3759, Nov. 2024, doi: 10.1080/00207543.2024.2427895.
Z. Hazim Obaid, B. Mirzaei, and A. Darroudi, “An efficient automatic modulation recognition using time–frequency information based on hybrid deep learning and bagging approach,” Knowledge and Information Systems, vol. 66, no. 4, pp. 2607–2624, Jan. 2024, doi: 10.1007/s10115-023-02041-y.
CRediT Author Statement
The authors confirm contribution to the paper as follows:
Conceptualization: Raied Qaied Ajmi, Layth Saleem Kamal and Ali Jasim Atiyah;
Methodology: Raied Qaied Ajmi and Layth Saleem Kamal;
Software: Layth Saleem Kamal and Ali Jasim Atiyah;
Data Curation: Raied Qaied Ajmi and Layth Saleem Kamal;
Writing- Original Draft Preparation: Raied Qaied Ajmi, Layth Saleem Kamal and Ali Jasim Atiyah;
Visualization: Layth Saleem Kamal and Ali Jasim Atiyah;
Investigation: Raied Qaied Ajmi and Layth Saleem Kamal;
Supervision: Layth Saleem Kamal and Ali Jasim Atiyah;
Validation: Raied Qaied Ajmi and Layth Saleem Kamal;
Writing- Reviewing and Editing: Raied Qaied Ajmi, Layth Saleem Kamal and Ali Jasim Atiyah;
All authors reviewed the results and approved the final version of the manuscript.
Acknowledgements
Author(s) thanks to Al-Furat Al-Awsat Technical University for research lab and equipment support.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of data and materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding author
Layth Saleem Kamal
Department of Mechanical Engineering, Babylon Technical Institute, Al-Furat Al-Awsat Technical University, Najaf, Iraq.
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this article
Raied Qaied Ajmi, Layth Saleem Kamal and Ali Jasim Atiyah, “Efficient Method for Gearbox Fault Diagnosis Under Variable Speed Conditions Using WVD Based Time Frequency Information of Vibration Signals and Deep Learning”, Journal of Machine and Computing, vol.6, no.1, pp. 253-265, 2026, doi: 10.53759/7669/jmc202606019.
