Performance Evaluation of the Time-Frequency Transformation Methods on Electrical Machinery Fault Detection

Abstract

Detecting faults in electrical machine systems is crucial for developing maintenance strategies. Modern technology enables personalized maintenance planning for system components by continuously or periodically monitoring systems with sensors. The first step in condition-based maintenance planning is predicting faults from sensor data. Monitoring vibration signals is one of the most preferred approaches for fault diagnosis in electrical machine systems. We have used a dataset containing vibration data recorded to detect intentionally created faults in an electrical machine system. The paper spots three popular methods to convert the time domain data into the frequency domain: power spectral density signal, spectrogram images, and scalogram images. Furthermore, we have analyzed the performance of the popular machine learning and deep learning methods with frequency-domain inputs. We have reported the results with accepted performance metrics such as accuracy, precision, recall, and F1 score. Our findings indicate that spectrogram images with the InceptionV3 model achieve maximum accuracy of over 98% accuracy among. The findings also highlight the necessity of carefully selecting model parameters based on the data type.

Keywords

• fault detection
• machine learning
• predictive maintenance
• time-frequency transform
• transfer learning
• vibration

Supporting Institution

TUBITAK 1507

Project Number

7220463

Ethical Statement

There is no conflict of interest between the authors.

Thanks

This work was supported by TUBITAK 1507 under grant number 7220463

References

1. R. Hu, J. Wang, A. R. Mills, E. Chong, and Z. Sun, "Current-residual-based stator interturn fault detection in permanent magnet machines," IEEE Transactions on Industrial Electronics, vol. 68, no. 1, pp. 59–69, 2020.
2. P. Nunes, J. Santos, and E. Rocha, "Challenges in predictive maintenance–A review," CIRP Journal of Manufacturing Science and Technology, vol. 40, pp. 53–67, 2023.
3. G. A. Susto, A. Schirru, S. Pampuri, S. McLoone, and A. Beghi, "Machine learning for predictive maintenance: A multiple classifier approach," IEEE Transactions on Industrial Informatics, vol. 11, no. 3, pp. 812–820, 2014.
4. S. Selcuk, "Predictive maintenance, its implementation and latest trends," Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, vol. 231, no. 9, pp. 1670–1679, 2017.
5. Y. Ran, X. Zhou, P. Lin, Y. Wen, and R. Deng, "A survey of predictive maintenance: Systems, purposes and approaches," arXiv preprint arXiv:1912.07383, 2019.
6. T. D. Popescu, D. Aiordachioaie, and A. Culea-Florescu, "Basic tools for vibration analysis with applications to predictive maintenance of rotating machines: an overview," The International Journal of Advanced Manufacturing Technology, pp. 1–17, 2022.
7. N. Vafaei, R. A. Ribeiro, and L. M. Camarinha-Matos, "Fuzzy early warning systems for condition based maintenance," Computers & Industrial Engineering, vol. 128, pp. 736–746, 2019.
8. G. Niu, X. Dong, and Y. Chen, "Motor Fault Diagnostics Based on Current Signatures: A Review," IEEE Transactions on Instrumentation and Measurement, 2023.

9. F. Al-Badour, M. Sunar, and L. Cheded, "Vibration analysis of rotating machinery using time–frequency analysis and wavelet techniques," Mechanical Systems and Signal Processing, vol. 25, no. 6, pp. 2083–2101, 2011.
10. J. R. Rivera-Guillen, J. De Santiago-Perez, J. P. Amezquita-Sanchez, M. Valtierra-Rodriguez, and R. J. Romero-Troncoso, "Enhanced FFT-based method for incipient broken rotor bar detection in induction motors during the startup transient," Measurement, vol. 124, pp. 277–285, 2018.
11. J. Dalzochio et al., "Machine learning and reasoning for predictive maintenance in Industry 4.0: Current status and challenges," Computers in Industry, vol. 123, p. 103298, 2020.
12. M. C. Garcia, M. A. Sanz-Bobi, and J. Del Pico, "SIMAP: Intelligent System for Predictive Maintenance: Application to the health condition monitoring of a wind turbine gearbox," Computers in Industry, vol. 57, no. 6, pp. 552–568, 2006.
13. F. Ribeiro, "MaFaulDa-machinery fault database," Signals, Multimedia, and Telecommunications Laboratory, 2016.
14. R. López-Valcarce, "General form of the power spectral density of multicarrier signals," IEEE Communications Letters, vol. 26, no. 8, pp. 1755–1759, 2022.
15. L. Niu and F. Li, "Cooperative Spectrum Sensing for Internet of Things Using Modeling of Power-Spectral-Density Estimation Errors," IEEE Internet of Things Journal, vol. 9, no. 10, pp. 7802–7814, 2021.
16. Z. Zhao, K. Peng, R. Xian, and X. Zhang, "Localization of Oscillation Source in DC Distribution Network Based on Power Spectral Density," Journal of Modern Power Systems and Clean Energy, vol. 11, no. 1, pp. 156–167, 2023.
17. S. Benkner, A. Herzog, S. Klir, W. D. Van Driel, and T. Q. Khanh, "Advancements in Spectral Power Distribution Modeling of Light-Emitting Diodes," IEEE Access, vol. 10, pp. 83612–83619, 2022.
18. "Signal Processing Toolbox," The MathWorks Inc., Available: https://www.mathworks.com/help/signal/ug/spectrogram-computation-with-signal-processing-toolbox.html (accessed February 1, 2024).