---

Journal of Vibration Testing and System Dynamics 10(4) (2026) 367--377 | DOI:10.5890/JVTSD.2026.12.005

Shaima Al Tubi, Al Zahraa Al Shmali, Ghim Al Farsi, Musaab Zarog

Department of Mechanical and Industrial Engineering, College of Engineering. Sultan Qaboos University, P.O. Box 33, Al-Khoud, Muscat, 123, Sultanate of Oman

Download Full Text PDF

 

Abstract

Fault detection can effectively reduce maintenance costs, unplanned downtime, manual inspection's errors, and safety hazards. of non-invasive mechanical fault identification This study explores machine learning techniques for automated fault classification using vibration data. A test rig was fabricated for this purpose. Various supervised learning algorithms, including Naïve Bayes, Logistic Regression, Deep Learning, Decision Trees, Random Forest, and Support Vector Machines (SVM), were evaluated for their classification accuracy. Additionally, Deep Learning Convolutional Neural Networks (CNNs) were applied to classify faults based on images of time-domain and frequency-domain vibration signals. Results indicate that frequency-domain images outperform time-domain images in fault identification, achieving an average accuracy of 50% compared to 23%. It was also demonstrated that the low accuracy achieved can be enhanced by increasing the size of dataset. This research demonstrates the potential of image-based AI-driven fault detection.

Acknowledgments

This work was funded by MOHERI fund in Oman [ref. RC/RG-ENG/MIED/23/03].

References

1. [1]	Bai, Y., Yang, J., Wang, J., Zhao, Y., and Li, Q. (2021), Image representation of vibration signals and its application in intelligent compound fault diagnosis in railway vehicle wheelset-axle box assemblies, Mechanical Systems and Signal Processing, 152, 107421.

2. [2]	Souza, R.M., Schettini, C.A.F., Almeida, F.E.M., de Araujo, F.R.R., and Callou, G. (2020), Deep learning for diagnosis and classification of faults in industrial rotating machinery, Computers & Industrial Engineering, 153, 107060.

3. [3]	Handikherkar, V.M.P.V.C. (2021), Gear fault detection using machine learning techniques: a simulation-driven approach, International Journal of Engineering, Transactions A: Basics, 34(1), 212-223.

4. [4]	Vives, J., Quiles, E., and García, E. (2020), AI techniques applied to diagnosis of vibrations failures in wind turbines, IEEE Latin America Transactions, 18(08), 1478-1486.

5. [5]	Macedo, L., Louzada, P., Villani, L.G.G., Frizera, A., Marques, C., and Leal-Junior, A. (2024), Machinery fault diagnosis in electric motors through mechanical vibration monitoring using fiber Bragg grating-based accelerometers, IEEE Sensors Journal, 24(13), 20655-20662.

6. [6]	Ahmed, H.O.A. and Nandi, A.K. (2022), Vibration image representations for fault diagnosis of rotating machines: a review, Machines, 10(12), 1113.

7. [7]	Nguyen, T.D., Nguyen, H.C., Pham, D.H., and Nguyen, P.D. (2024), A distinguished deep learning method for gear fault classification using time-frequency representation, SN Applied Sciences, 6(1), 33.

8. [8]	Yan, H., Yu, H., Zhu, S., Yin, Y., and Guo, L. (2024), Machine learning-based framework for rapid forecasting of crack propagation, Engineering Fracture Mechanics, 276, 110278.

9. [9]	Xu, Y., Zhao, Y., and Li, Y. (2022), Machine-learning-based deformation prediction method for deep foundation-pit enclosure structure, Applied Sciences, 14(3), 1273.

10. [10]	R, M. and Mutra, R.R. (2025), Fault classification in rotor-bearing systems using advanced signal processing and machine learning techniques, Results in Engineering, 25, 103892.

11. [11]	Khan, M.A., Asad, B., Kudelina, K., Vaimann, T., and Kallaste, A. (2022), The bearing faults detection methods for electrical machines-the state of the art, Energies, 16(1), 296.

12. [12]	Janssens, O., Slavkovikj, V., Vervisch, B., Stockman, K., Loccufier, M., Verstockt, S., Van de Walle, R., and Van Hoecke, S. (2016), Convolutional neural network-based fault detection for rotating machinery, Journal of Sound and Vibration, 377, 331-345.

13. [13]	Balaji, M.A., Venkatesh, S.N., Sugumaran, V., and Ramachandran, K.I. (2025), A comparative study of image representation for roller bearing fault diagnosis using pretrained networks, Journal of Engineering, 2025(1).

14. [14]	Lan, C. and Shi, X. (2024), Multi-domain feature fusion in CNNs for fault diagnosis of rotating machinery under noisy conditions, Journal of Vibroengineering, 26(2), 1122-1135.

15. [15]	Luo, T., Qiu, M., Wu, Z., Zhao, Z., and Zhang, D. (2025), Bearing fault diagnosis based on multi-scale spectral images and convolutional neural network, Journal of Vibroengineering, 27(6), 1012-1027.

16. [16]	Aiordachioaie, D. (2024), A comparative analysis of fault detection and process diagnosis methods based on a signal processing paradigm, Discover Applied Sciences, 7(1), 10.