Journal Press India^®

Author Details ( * ) denotes Corresponding author

This study addresses the critical need for reliable gearbox fault detection in industrial machinery, aiming to enhance operational efficiency and reduce downtime. The research explores the application of deep learning techniques, specifically focusing on the InceptionResNetV2 transfer learning model, for analysing vibration signals using Constant Q Transform (CQT) spectrograms. CQT’s adaptive resolution and noise robustness make it superior for capturing time-varying frequency content in non-stationary signals, such as those from gearboxes. The custom dataset, derived from SpectraQuest’s Gearbox Fault Diagnostics Simulator, includes labeled CQT spectrograms of healthy and faulty gearboxes, preprocessed and augmented for model training. The InceptionResNetV2 architecture, combining Inception modules and residual connections, effectively captures multiscale features, achieving 98.04% accuracy in fault classification. Evaluation metrics, including precision, recall, and F1 score, confirm the model’s robustness. Comparative analysis with other methods highlights its superiority in handling limited data and noisy conditions. This work demonstrates the viability of transfer learning-based fault detection systems for industrial applications, offering a template for predictive maintenance solutions. Future improvements will focus on multi-modal fusion and explainable AI techniques for enhanced interpretability.

Keywords

Gearbox Fault Detection; Deep Learning; Constant Q Transform (CQT); Transfer Learning; Vibration Analysis

1. Bliznyuk, A. S., Dadon, I. S., Klein, R. S. & Bortman, J. (2014). Gear diagnostics - Fault type characteristics. Annual Conference of the PHM Society, 6(1). Retrieved from https://doi.org/10.36001/phmconf.2014.v6i1.2386
2. Ghanbari, N., Riyazi, Y., Shirazi, F. A. & Kalhor, A. (2023). Enhanced gearbox fault diagnosis with fusion LSTM-CNN network. International Conference on Acoustics and Vibrations, Tehran, Iran. Retrieved from https://www.researchgate.net/publication/377217896_Enhanced_Gearbox_Fault_Diagnosis_with_Fusion_LSTM-CNN_Network
3. Hakim, M.S., Omran, A.A.B., Ahmed, A.N., Al-Wally, M.S. & Abdellatif, A. (2023). A systematic review of rolling bearing fault diagnoses based on deep learning and transfer learning: Taxonomy, overview, application, open challenges, weaknesses and recommendations. Ain Shams Engineering Journal, 14(4), 101945. Retrieved from https://doi.org/10.1016/j.asej.2022.101945
4. Kumar, S., Goyal, D., Dang, R.K., Dhami, S.S. & Pabla, B.S. (2018). Condition-based maintenance of bearings and gears for fault detection - A review. Materiolstoday Proceedings, 5(2):6128-37. Retrieved from https://doi.org/10.1016/j.matpr.2017.12.219
5. Li, H., Ly, Y., Yuan, R., Dang, Z., Cai, Z. & An, B. (2022). Fault diagnosis of planetary gears based on intrinsic feature extraction and deep transfer learning. Measurement Science and Technology, 34(1), 014009. Retrieved from https://doi.org/10.1088/1361-6501/ac9543
6. Liao, W.S. & De Geest, R. (2024). Active learning for gear defect detection in gearboxes. Proceedings of the European Conference of the PHM Soceity, 8(1), 10. Retrieved from https://doi.org/10.36001/phme.2024.v8i1.4050
7. Liu, G., Bao, H. & Han, B. (2018). A stacked autoencoder-based deep neural network for achieving gearbox fault diagnosis. Mathematical Problems in Engineering. Retrieved from https://doi.org/10.1155/2018/5105709
8. Liu, H., Li. L. & Ma, J. (2016). Rolling bearing fault diagnosis based on STFT-deep learning and sound signals. Shock and Vibration. Retrieved from https://doi.org/10.1155/2016/6127479
9. Mohammed, O.D. & Rantatalo, M. (2020). Gear fault models and dynamics-based modelling for gear fault detection - A review. Engineering Failure Analysis, 117, 104798. Retrieved from https://doi.org/10.1016/j.engfailanal.2020.104798
10. Neupane, D., Bouadjenek, M.R., Dazeley, R. & Aryal, S. (2024). Data-driven machinery fault detection: A comprehensive review. Retrieved from http://dx.doi.org/10.2139/ssrn.4856168
11. Nguyen, T.-D., Nguyen, H.-C., Pham, D.-H. & Nguyen, P.-D. (2024). A distinguished deep learning method for gear fault classification using time-frequency representation. Discover Applied Science, 6(7), 340. Retrieved from https://doi.org/10.1007/s42452-024-06033-7
12. Qian, Q., Qin, Y., Luo, J. & Wang, S. (2022). Partial transfer fault diagnosis by multiscale weight-selection adversarial network. IEEE/ASME Transactions on Mechatronics, 27(6), 4798-4806. Retrieved from https://doi.org/10.1109/TMECH.2022.3166977
13. Ramteke, D.S., Parey, A. & Pachori, R.B. (2023). A new automated classification framework for gear fault diagnosis using Fourier-Bessel domain-based empirical wavelet transform. Machines, 11(12), 1055. Retrieved from https://doi.org/10.3390/machines11121055
14. Schmidt, S., Wilke, D.N. & Gryllias, K.C. (2025). Generalised envelope spectrum-based signal-to-noise objectives: Formulation, optimisation and application for gear fault detection under time-varying speed conditions. Machines, 11(12), 1055. Retrieved from https://doi.org/10.3390/machines11121055
15. Stockwell, R.G., Mansinha, L. & Lowe, R.P. (1996). Localization of the complex spectrum: The S transform. IEEE Transactions on Signal Processing, 44(4), 998-1001. Retrieved from https://doi.org/10.1109/78.492555
16. Wang, T., Zhang, L., Qiao, H. & Wang, P. (2019). Fault diagnosis of rotating machinery under time-varying speed based on order tracking and deep learning. Journal of Vibroengineering, 22(2), 366-382. Retrieved from https://doi.org/10.21595/jve.2019.20784
17. Xu, L., Wang, T., Xie, J., Yang, J. & Gao, G. (2022). A mechanism-based automatic fault diagnosis method for gearboxes. Sensors, 22(23), 9150. Retrieved from https://doi.org/10.3390/s22239150
18. Xu, Y., Yan, X., Sun, B., Zhai, J. & Liu, Z. (2022). Multireceptive field denoising residual convolutional networks for fault diagnosis. IEEE Transactions on Industrial Electronics, 69(1), 11686-11696. Retrieved from https://doi.org/10.1109/TIE.2021.3125666. 
19. Zhang, X., Xu, Q., Jiang, H. & Li, J. (2023). Application of deep neural network in gearbox compound fault diagnosis. Energies, 16(10), 4164. Retrieved from https://doi.org/10.3390/en16104164
20. Zhou, A.Y. & Farimani, A.B. (2024). FaultFormer: Pretraining transformers for adaptable bearing fault classification. IEEE Access, 12(2), 70719-70728. Retrieved from https://doi.org/10.1109/ACCESS.2024.3399670