Е-Публикации
Технически университет - София

Abstract: The classification of sound signals can be applied to the fault diagnosis of electromechanical devices and systems, such as electrical machines, drives, production machines, etc. Traditional methods identify acoustic signals by analyzing their characteristics in both the time and frequency domains. This paper focuses on one of the latest trends for visualizing sound signals which can then be used by image classification models for fault detection in electrical machines and drives. The experiment described uses an electric motors sound recording dataset together with Domain Generalization approach based on Symmetrized Dot Pattern. Image classification is utilized to distinguish the different conditions of the electric motors. The results suggest that the presented approach could be a fast and cost-effective method for electrical machine diagnostics. Despite the promising outcomes, further work can be done based on more versatile data and different image classification models relying on autoencoders or convolutional neural networks together with large language models.

References

1. "Energy efficiency", IEA, 2020, https://iea.blob.core.windows.net/assets/59268647-0b70-4e7b-9f78-269e5ee93f26/Energy-Efficiency-2020.pdf.
2. R. Junior, Isac Areias, M. Campos, C. Teixeira, L. Silva and G. Gomes, "Fault detection and diagnosis in electric motors using 1d convolutional neural networks with multi-channel vibration signals", Measurement, Vol. 190, 2022, DOI:10.1016/j.measurement. 2022.110759.
3. K. Belda, V. Rychnovsky and P. Pisa, "Wireless communication for control of manipulation systems", Archives of Control Sciences, Vol. 22, No. 1, pp. 29-41, 2012, ISSN 1230-2384.
4. M. Mikhov, N. Stoyanov, G. Stanchev and Z. Doichev, "An application of wireless standards for remote monitoring of electric drive systems", International Journal of Engineering Research and Development, Vol. 2, No. 12, pp. 30-36, 2012, ISSN 2278-800X.
5. N. Stoyanov, M. Mikhov and G. Stanchev, "Remote wireless monitoring of an electric drive system", International Journal of Science and Advanced Technology, Vol. 2, No. 9, pp. 42-45, 2012, ISSN 2304-652X.
6. N. Koteleva and N. Korolev, "A diagnostic curve for online fault detection in AC drives", Energies, Vol. 17, Issue 5, 2024, DOI: 10.3390/en17051234.7.?
7. M. Gultekin and A. Bazzi, "Review of fault detection and diagnosis techniques for AC motor drives", Energies, Vol. 16, Issue 15, 2023, DOI: 10.3390/en16155602.
8. P. Mobtahej, X. Zhang, M. Hamidi and J. Zhang, "An LSTMautoencoder architecture for anomaly detection applied on compressors audio data", Computational and Mathematical Methods, Vol. 2022, pp. 1-22, DOI: 10.1155/2022/3622426.
9. A. Glowacz, "Fault diagnosis of single-phase induction motor based on acoustic signals", Mechanical Systems and Signal Processing, Vol. 117, pp. 65-80, 2019, DOI: 10. 1016/j.ymssp.2018.07.044.
10. G. Jombo and Y. Zhang, "Acoustic-based machine condition monitoring-methods and challenges", Eng, Vol. 4, No. 1, pp. 47-79, 2023, DOI: 10.3390/eng4010004.
11. J.-D. Wu, W.-J. Luo and K.-C. Yao, "Acoustic signal classification using symmetrized dot pattern and convolutional neural network", Machines, Vol. 10, Issue 2, 2022, DOI: 10.3390/machines10020090.
12. G. Lucas, et al., "Fault diagnosis of electrical faults of three phase induction motors using acoustic analysis", Bulletin of the Polish Academy of Sciences Technical Sciences, pp. 148440-148440, 2024. DOI: 10.24425/bpasts.2024.148440.
13. R. Grandhi and N. Prakash, "Machine-learning based fault diagnosis of electrical motors using acoustic signals", Data Intelligence and Cognitive Informatics, 2021, DOI: 10.1007/978-981-15-8530-2-52.
14. P. Kumar and A. Hati, "Review on machine learning algorithm based fault detection in induction motors", Archives of Computational Methods in Engineering, Vol. 28, pp. 1929-1940, 2021, DOI: 10.1007/s11831-020-09446-w.
15. M.-H. Wang, S.-D. Lu and C.-C. Hung, "Application of deep learning and symmetrized dot pattern to detect surge arrester status", Applied Sciences, Vol. 12, Issue 2, 2022, DOI: 10.3390/app12020650.
16. B. Pang, J. Liang, H. Liu, J. Dong, Z. Xu and X. Zhao, "Intelligent bearing fault diagnosis based on multivariate symmetrized dot pattern and LEG transformer", Machines, Vol. 10, Issue 7, 2022, DOI: 10.3390/machines10070550.
17. W. Cui, G. Meng, T. Gou, A. Wang, R. Xiao and X. Zhang, "Intelligent rolling bearing fault diagnosis method using symmetrized dot pattern images and CBAM-DRN", Sensors, Vol. 22, Issue 24, 2022, DOI: 10.3390/s22249954.
18. L. Huang, J. Wen, Y. Yang, L. Chen and G. Shen, "A visual fault detection method for induction motors based on a zero-sequence current and an improved symmetrized dot pattern", Entropy, Vol. 24, Issue 5, 2022, DOI: 10.3390/e24050614.
19. A. Krizhevsky, I. Sutskever and G. Hinton, "ImageNet classification with deep convolutional neural networks", Comunications of the ACM, Vol. 60, Issue 6, pp. 84-90, DOI: 10.1145/3065386.
20. DCASE, [Online]. Available: https://dcase.community/.
21. S. Grollmisch, J. Abeßer, J. Liebetrauand and H. Lukashevich, "IDMTISA-electric-engine dataset", Zenodo, Sep. 01, 2019. DOI: 10.5281/zenodo.7551261.
22. K. Strantzalis, F. Gioulekas, P. Katsaros and A. Symeonidis, "Operational state recognition of a DC motor using edge artificial intelligence", Sensors, Vol. 22, Issue 24, 2022, DOI: 10.3390/s22249658.

Issue