Autors: Yordanov, N. I., Zhilevski, M. M., Mikhov, M. R., Ertargin M.
Title: A Hybrid Machine Learning Architecture for Acoustic Fault Diagnosis in Electric Motors: Offline and Online Modes via Mobile Phone
Keywords: acoustic data, classification, CNN-based models, electric motor, embedded machine learning models, mobile app, SDP method

Abstract: This paper proposes a hybrid ML architecture for non-invasive acoustic fault diagnosis in electric motors and machines using a.NET MAUI cross-platform mobile app for short audio capture (5-20s), audio-to-image transformations and dual-mode inference: embedded ML.NET/ONNX models for offline preliminary detection and Azure ML-hosted deep CNN/RNN for online probabilistic multi-fault analysis. The primary objective of this paper is to demonstrate the benefits of the proposed architecture and to show the specific tools which can be used for implementation. Architectures (embedded, cloud, hybrid) are evaluated by listing main advantages and disadvantage, highlighting hybrid approach that combines offline resilience, reduced latency and keeping the possibility for complex analysis by using online hosted model. Sample mobile application design is added to showcase the proposed user experience.

References

  1. G. Eason, B. Noble, and I. N. Sneddon, “On certain integrals of Lipschitz-T. Kawady, W. M. Khater, H. G. Abu-Faty, et al.,”AI driven fault diagnosis approach for stator turn to turn faults in induction motors”, Sci Rep 15, 20125, 2025, https://doi.org/10.1038/s41598-025-04462-x.
  2. B. Xu, H. Li, R. Ding, and F. Zhou, “Fault diagnosis in electric motors using multi-mode time series and ensemble transformers network”, Scientific reports, 15(1), 7834, 2025, https://doi.org/10.1038/s41598-025-89695-6.
  3. S. M. Yoo, H. G. Lee, W. K. Hao and I. S. Lee, “Induction Motor Fault Diagnosis Using Low-Cost MEMS Acoustic Sensors and Multilayer Neural Networks”, Applied Sciences, 15(17), 9379, 2025, https://doi.org/10.3390/app15179379.
  4. Y. Liu, Z. Xu, Y. He, P. Guo and K. Mu, “Acoustic fault diagnosis method for rotating machinery based on improved spectral subtraction and CNN-TCN model”, Measurement 2025, 2025, https://doi.org/10.1016/j.measurement.2025.118482.
  5. A. Glowacz, M. Sulowicz, J. Zielonka, Z. Li, W. Glowacz and A. Kumar, “Acoustic fault diagnosis of three-phase induction motors using smartphone and deep learning”, Expert Systems With Applications, 262, 125633, 2024, https://doi.org/10.1016/j.eswa.2024.125633.
  6. N. Yordanov, M. Zhilevski and M. Mikhov, “Fault Detection in Electric Motors using Acoustic Signals and Image Classification”, Proceedings of the 2024 International Conference on Applied and Theoretical Electricity (ICATE), pp. 1-6, Craiova, Romania, IEEE Xplore, 2024, DOI: 10.1109/ICATE62934.2024.10749208.
  7. S. M. Yoo, H.G. Lee, W. K. Hao and I. S. Lee, “Induction Motor Fault Diagnosis Using Low-Cost MEMS Acoustic Sensors and Multilayer Neural Networks”, Applied Sciences, 15(17), 9379, 2025, https://doi.org/10.3390/app15179379.
  8. K. Huang and Q. Chen, “Motor Fault Diagnosis and Predictive Maintenance Based on a Fine-Tuned Qwen2.5-7B Model”, Processes, 13(7), 2051, 2025, https://doi.org/10.3390/pr13072051.
  9. L. Xu, S. S. Teoh and H. Ibrahim, “A deep learning approach for electric motor fault diagnosis based on modified InceptionV3”, Sci Rep 14, 12344, 2024, https://doi.org/10.1038/s41598-024-63086-9
  10. S. Heydari and Q. H. Mahmoud, “Tiny Machine Learning and On-Device Inference: A Survey of Applications, Challenges, and Future Directions”, Sensors, Basel, Switzerland, 25(10), 3191, 2025, https://doi.org/10.3390/s25103191.
  11. 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, 22(24), 9954, 2022, https://doi.org/10.3390/s22249954
  12. G. Liang, X. Song, Z. Liao and B. Jia, “Optimal Time Frequency Fusion Symmetric Dot Pattern Bearing Fault Feature Enhancement and Diagnosis”, Sensors, 24(13), 4186, 2024, https://doi.org/10.3390/s24134186.
  13. S. Arciniegas, D. Rivero, J. Piñan, et al., “IoT device for detecting abnormal vibrations in motors using TinyML: Discov Internet Things 5”, 41, 2025, https://doi.org/10.1007/s43926-025-00142-4.
  14. K. Aung and C. Kok, Y. Koh and T. H. Teo, “An Embedded Machine Learning Fault Detection System for Electric Fan Drive. Electronics”, 13. 493, 2024, https://doi.org/10.3390/electronics13030493.
  15. “Predictive Maintenance Market Size & Share Report [2032]”, 2025, [online] Available: https://www.fortunebusinessinsights.com/predictivemaintenance-market-102104.
  16. “Predictive Maintenance Market Size | Industry Report [2030]”, 2025, [online] Available: https://www.grandviewresearch.com/industryanalysis/predictive-maintenance-market
  17. C. Zachariades and V. Xavier, “A Review of Artificial Intelligence Techniques in Fault Diagnosis of Electric Machines”, Sensors, 25(16), 5128, 2025 https://doi.org/10.3390/s25165128.
  18. “What is .NET MAUI?”, 2025, [online] Available: https://learn.microsoft.com/en-us/dotnet/maui/what-is-maui?view=netmaui-9.0 .
  19. “What is ML.NET and how does it work?”, 2025, [online] Available: https://learn.microsoft.com/en-us/dotnet/machine-learning/mldotnet-api.
  20. “ONNX”, 2025, [online] Available: https://onnx.ai/.
  21. “Azure Machine Learning,” 2025, [online] Available: https://azure.microsoft.com/en-us/products/machine-learning.
  22. “Figma”, 2025, [online] Available: https://www.figma.com/make/.

Issue

International Conference on Engineering and Emerging Technologies, ICEET, pp. 1-6, 2026, Malaysia, https://doi.org/10.1109/ICEET67911.2025.11424092

Copyright IEEE Xplore

Вид: статия в списание, публикация в реферирано издание, индексирана в Scopus