Е-Публикации
Технически университет - София

Abstract: Published by Cefin Publishing House.This study examines the impact of foundation stability on electric motor vibrations and noise fingerprint at 500–2000 RPM using continuous vibration data from vibration sensor and audio recordings from mobile phone. The aim of the research is to evaluate the effectiveness of using audio analysis as a substitute for vibration data. Another focus of the study is to compare Symmetrized Dot Pattern (SDP) with mel-spectrogram for classifying acoustic data. Both discrete (low sample count) and continuous vibration signal data are collected using vibration meter directly attached to an electric motor cage. In parallel, noise recordings are performed using mobile phone. Valuable insights in the study are provided by the observation of the relations between vibration values for displacement, velocity and acceleration in a state of loosened electric motor foundation. Employing convolutional neural networks (CNNs) like ResNet, the study achieved up to 98% accuracy in classifying operational states and faults using audio-to-image transformations (vibration data) and highlighting the potential of hybrid vibro-acoustic diagnostics for monitoring and predictive maintenance. As conclusion is found that noise audio recording together with machine learning models and image transformations can be a valuable tool for preliminary non-invasive checks, offering a cost-effective and accessible means to detect initial faults in electrical machines.

References

1. Yakovenko, I., Permyakov, A., Dobrotvorskiy, S., Basova Y., Kotliar, A., & Zinchenko, A. (2023). Prospects for the development of process equipment in aggregate-modular design for sustainable mechanical engineering. International Journal of Mechatronics and Applied Mechanics: Issue 13, (pp. 145–156). https://dx.doi.org/10.17683/ijomam/issue13.18
2. Basova, Y., Dobrotvorskiy, S., Balog, M., Iakovets, A., Amine, C.M., & Zinchenko, A. (2023). Increasing SME Supply Chain Resilience in the Face of Rapidly Changing Demand with 3D Model Visualisation. International Journal of Mechatronics and Applied Mechanics, 14, 35–47. https://doi.org/10.17683/ijomam/issue14.5
3. Shubita, R., Alsadeh, A. & Khater, I. (2023). Fault detection in rotating machinery based on sound signal using edge machine learning. IEEE Access, 11, 6665-6672. https://doi.org/10.1109/ACCESS.2023.3237074
4. ElAraby, W., Madian, A. & Saad, M. (2025). Fault diagnosis for rotating machinery based on deep learning. Noise & Vibration Worldwide, 56, 400–421. https://doi.org/10.1177/09574565251348863
5. Wang, X., Mao, D., & Li, X. (2021). Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network, Measurement, 173, 108518. https://doi.org/10.1016/j.measurement.2020.108518
6. Ertarğın, M., Yildirim, Ö., & Orhan, A. (2024). Mechanical and electrical faults detection in induction motor across multiple sensors with CNN-LSTM deep learning model. Electrical Engineering, 106, 6941-6951. https://doi.org/10.1007/s00202-024-02420-w
7. Cui, W., Meng, G., Gou, T., Wang, A., Xiao, R., & Zhang, X. (2022). Intelligent rolling bearing fault diagnosis method using symmetrized dot pattern images and CBAM-DRN. Sensors, 22, 9954. https://doi.org/10.3390/s22249954
8. Wang, H., Xu, J., Yan, R., & Gao, R. (2020). A New Intelligent Bearing Fault Diagnosis Method Using SDP Representation and SE-CNN. IEEE Transactions on Instrumentation and Measurement, 69(5), 2377-2389. https://doi.org/10.1109/TIM.2019.2956332
9. Diwakar, A., & Manivannan, P. (2019). Symmetrised dot pattern technique for fault diagnosis in a spur gear assembly using vibration signals. IOP Conference Series: Materials Science and Engineering, 561, 012079. https://doi.org/10.1088/1757-899X/561/1/012079
10. Shaikh, K., Jawarkar, N., Ahmed, V., & Charniya, N. (2025). Audio anomaly detection in industrial machines using inverse-Mel scale spectrograms. Systems and Soft Computing, 7, 200398. https://doi.org/10.1016/j.sasc.2025.200398
11. Bin Saharom, A., & Ehara, F. (2024). Comparative Analysis of MFCC and Mel-Spectrogram Features in Pump Fault Detection Using Autoencoder. 2024 2nd International Conference on Computer Graphics and Image Processing (CGIP). IEEE. 124–128. https://doi.org/10.1109/CGIP62525.2024.00030
12. Mian, T., Choudhary, A., Fatima, S., & Panigrahi, B. (2023). Mel-spectrogram based Approach for Fault Detection in Ball Bearing using Convolutional Neural Network. ICECC '23, 283– 289. https://doi.org/10.1145/3592307.3592352
13. de Walque, C., & Jamaluddin, R. (2023). Vibro-acoustic Study of a Full Vehicle Excited by an Electric Motor: Structure-borne and Air-borne Noise Comparison. SAE Technical Paper 2023-01-1112. https://doi.org/10.4271/2023-01-1112
14. Król, E., Maciążek, M., & Wolnik, T. (2023). Review of Vibroacoustic Analysis Methods of Electric Vehicles Motors. Energies, 16, 2041. https://doi.org/10.3390/en16042041
15. Yang, C., Gan, X., Peng, A., & Yuan, X. (2023). ResNet Based on Multi-Feature Attention Mechanism for Sound Classification in Noisy Environments. Sustainability, 15, 10762. https://doi.org/10.3390/su151410762
16. Rashed, A., Abdulazeem, Y., Farrag, T., Bamaqa, A., Almaliki, M., Badawy, M., & Elhosseini, M. (2025). Toward Inclusive Smart Cities: Sound-Based Vehicle Diagnostics, Emergency Signal Recognition, and Beyond. Machines, 13, 258. https://doi.org/10.3390/machines13040258
17. Yang, D., Lv, Y., Yuan, R., Yang, K., & Zhong, H. (2022). A novel vibro-acoustic fault diagnosis method of rolling bearings via entropy-weighted nuisance attribute projection and orthogonal locality preserving projections under various operating conditions. Appl. Acoust., 196, 108889. https://doi.org/10.1016/j.apacoust.2022.108889
18. Tiboni, M., Remino, C., Bussola, R., & Amici, C. (2022). A Review on Vibration-Based Condition Monitoring of Rotating Machinery. Appl. Sci., 12, 972. https://doi.org/10.3390/app12030972
19. Romanssini, M., de Aguirre, P.; Compassi-Severo, L., & Girardi, A. (2023). A Review on Vibration Monitoring Techniques for Predictive Maintenance of Rotating Machinery. Eng, 4(3), 1797-1817. https://doi.org/10.3390/eng4030102
20. Ertarğın, M., Yordanov, N., & Zhilevski, M. (2025). Health Status Classification of Electric Motors Using CNN-Based Models and SDP Images Under Varying Noise Conditions. Presented at: 11th World Congress on Electrical Engineering and Computer Systems and Science, Paris, France. https://doi.org/10.11159/eee25.107
21. Orhan, A., Yordanov, N., Ertarğın, M., Zhilevski, M., & Mikhov, M. (2025). A Comparative Study of Time–Frequency Representations for Bearing and Rotating Fault Diagnosis Using Vision Transformer. Machines, 13(8), 737. https://doi.org/10.3390/machines13080737
22. Faulhaber, 2025, [online] Available: https://ell-bg.com/en/products/servo-drives/12-13-14xxx-series-digital-thyristor-converters-for-controlling-permanent-magnet-dc-motors/
23. Krol, O. (2021). Modeling of Worm Gear Design with Non-clearance Engagement. In: A.A. Radionov, & V.R. Gasiyarov (Eds.) Proceedings of the 6th International Conference on Industrial Engineering (ICIE 2020). LNME (pp. 36–46). Springer, Cham. https://doi.org/10.1007/978-3-030-54814-8_5
24. Shevchenko, S., Mukhovaty, A., & Krol, O. (2021). Modification of Two-Stage Coaxial Gearbox. In: A.A. Radionov, & V.R. Gasiyarov, (Eds.) Proceedings of the 6th International Conference on Industrial Engineering (ICIE 2020) (pp. 28–35). Springer, Cham. https://doi.org/10.1007/978-3-030-54814-8_4
25. Jombo, G., & Zhang, Y. (2023). Acoustic-Based Machine Condition Monitoring—Methods and Challenges, Eng, 4(1), 47-79. https://doi.org/10.3390/eng4010004

Issue

Copyright International Journal of Mechatronics and Applied Mechanics – IJOMAM