Journal of Radio Electronics. eISSN 1684-1719. 2024. ¹12

Contents

Full text in Russian (pdf)

Russian page

 

 

DOI: https://doi.org/10.30898/1684-1719.2024.12.8

 

 

 

PROJECTION METHOD FOR OUTLIER DETECTION

IN SENSOR DATA IN VIBROACOUSTICS PROBLEMS

 

N.A. Kutuzov, A.A. Rodionov

 

A.V. Gaponov-Grekhov Institute of Applied Physics of the Russian Academy of Sciences (IAP RAS)

603950, Russia, Nizhny Novgorod, Ul'yanov Street, 46

 

The paper was received August 20, 2024

 

Abstract. A common problem in measurements using a set of vibration sensors in vibroacoustics is the lack of an accurate signal model on the receivers. Such uncertainty can lead to processing algorithms errors and an incorrect solution to the inverse problem. Due to a malfunction, vibration sensors data can also be bad, deteriorating the quality of measurements. In practice, the search for such anomalous sensors is a non-trivial task. In this paper, an original method related to projection algorithms is proposed for this problem. It is shown that the proposed method allows detecting anomalous sensors of various types. The method main feature is using both numerical finite element model of the object and experimental data. The efficiency of the proposed method is demonstrated in the localizing vibration sources problem. The new method can be used in other applications where the inverse problem is solved using a numerical or analytical model.

Key words: projection methods, noise and vibration, source localization, fault detection, outlier detection, sensor data.

Financing: Funded by FFUF-2024-0040.

Corresponding author: Kutuzov Nikita Anatolievich, nik-kutuzov@yandex.ru

 

References

1. Petyt M. Introduction to finite element vibration analysis. – Cambridge university press,2010. https://doi.org/10.1017/CBO9780511761195

2. Pastor M., Binda M., Harčarik T. Modal assurance criterion //Procedia Engineering. – 2012. – Ò. 48. – Ñ. 543-548. https://doi.org/10.1016/j.proeng.2012.09.551

3. Lee E. T., Eun H. C. Optimal sensor placements using modified Fisher information matrix and effective information algorithm //International Journal of Distributed Sensor Networks. – 2021. – Ò. 17. – ¹. 6. https://doi.org/10.1177/15501477211023022

4. Heo G., Wang M. L., Satpathi D. Optimal transducer placement for health monitoring of long span bridge //Soil dynamics and earthquake engineering. – 1997. – Ò. 16. – ¹. 7-8. – Ñ. 495-502. https://doi.org/10.1016/S0267-7261(97)00010-9

5. Teh H. Y., Kempa-Liehr A. W., Wang K. I. K. Sensor data quality: A systematic review //Journal of Big Data. – 2020. – Ò. 7. – ¹. 1. – Ñ. 11. https://doi.org/10.1186/s40537-020-0285-1

6. Hotelling H. Analysis of a complex of statistical variables into principal components //Journal of educational psychology. – 1933. – Ò. 24. – ¹. 6. – Ñ. 417. https://doi.org/10.1037/h0071325

7. De Boe P., Golinval J. C. Principal component analysis of a piezosensor array for damage localization //Structural health monitoring. – 2003. – Ò. 2. – ¹. 2. – Ñ. 137-144. https://doi.org/10.1177/1475921703002002005

8. Golub G. H., Van Loan C. F. Matrix computations. – JHU press, 2013. https://doi.org/10.1137/1.9781421407944

9. Pirra M. et al. PCA algorithm for detection, localisation and evolution of damages in gearbox bearings //Journal of Physics: Conference Series. – IOP Publishing, 2011. – Ò. 305. – ¹. 1. https://doi.org/10.1088/1742-6596/305/1/012019

10. Tibaduiza D. et al. A sensor fault detection methodology applied to piezoelectric active systems in structural health monitoring applications //IOP Conference Series: Materials Science and Engineering. – IOP Publishing, 2016. – Ò. 138. – ¹. 1. https://doi.org/10.1088/1757-899X/138/1/012016

11. Dunia R. et al. Use of principal component analysis for sensor fault identification //Computers & Chemical Engineering. – 1996. – Ò. 20. – Ñ. S713-S718. https://doi.org/10.1016/0098-1354(96)00128-7

12. Xu C., Zhao S., Liu F. Sensor fault detection and diagnosis in the presence of outliers //Neurocomputing. – 2019. – Ò. 349. – Ñ. 156-163. https://doi.org/10.1016/j.neucom.2019.01.025

13. Abu-Mahfouz I. Drilling wear detection and classification using vibration signals and artificial neural network //International Journal of Machine Tools and Manufacture. – 2003. – Ò. 43. – ¹. 7. – Ñ. 707-720. https://doi.org/10.1016/S0890-6955(03)00023-3

14. Zonzini F. et al. Machine learning meets compressed sensing in vibration-based monitoring //Sensors. – 2022. – Ò. 22. – ¹. 6. – Ñ. 2229. https://doi.org/10.3390/s22062229

15. Zhu K., San Wong Y., Hong G. S. Wavelet analysis of sensor signals for tool condition monitoring: A review and some new results //International Journal of Machine Tools and Manufacture. – 2009. – Ò. 49. – ¹. 7-8. – Ñ. 537-553. https://doi.org/10.1016/j.ijmachtools.2009.02.003

16. Diez A. et al. A clustering approach for structural health monitoring on bridges //Journal of Civil Structural Health Monitoring. – 2016. – Ò. 6. – Ñ. 429-445. https://doi.org/10.1007/s13349-016-0160-0

17. Žvokelj M., Zupan S., Prebil I. Multivariate and multiscale monitoring of large-size low-speed bearings using ensemble empirical mode decomposition method combined with principal component analysis //Mechanical Systems and Signal Processing. – 2010. – Ò. 24. – ¹. 4. – Ñ. 1049-1067. https://doi.org/10.1016/j.ymssp.2009.09.002

18. Kutuzov N. A. et al. Study of the possibility of localizing multiple vibration sources in a mechanoacoustic system with a large number of degrees of freedom //Acoustical Physics. – 2020. – Ò. 66. – Ñ. 313-319. https://doi.org/10.1134/S1063771020030033

19. Kutuzov N. A., Rodionov A. A., Stulenkov A. V. Localization of Multiple Vibration Sources Using a Modified MUSIC Algorithm //Physics of Wave Phenomena. – 2024. – Ò. 32. – ¹. 1. – Ñ. 56-66. https://doi.org/10.3103/S1541308X24010059

20. Goutaudier D., Osmond G., Gendre D. Impact localization on a composite fuselage with a sparse network of accelerometers //Comptes Rendus. Mécanique. – 2020. – Ò. 348. – ¹. 3. – Ñ. 191-209. https://doi.org/10.5802/crmeca.12

21. Turek G., Kuperman W. A. Applications of matched-field processing to structural vibration problems //The Journal of the Acoustical Society of America. – 1997. – Ò. 101. – ¹. 3. – Ñ. 1430-1440 https://doi.org/10.1121/1.418168

22. Lukovskiy M. A., Matveev A. M. Comparative analysis methods calibration channels signal antennas monopulse radiolocation// Journal of Radio Electronics. – 2022. – ¹6. https://doi.org/10.30898/1684-1719.2022.6.5

23. Valle S., Li W., Qin S. J. Selection of the number of principal components: the variance of the reconstruction error criterion with a comparison to other methods //Industrial & Engineering Chemistry Research. – 1999. – Ò. 38. – ¹. 11. – Ñ. 4389-4401. https://doi.org/10.1021/ie990110i

24. Leys C. et al. Detecting outliers: Do not use standard deviation around the mean, use absolute deviation around the median //Journal of experimental social psychology. – 2013. – Ò. 49. – ¹. 4. – Ñ. 764-766. https://doi.org/10.1016/j.jesp.2013.03.013

25. Suvorov A. S., Sokov E. M., V’yushkina I. A. Regular algorithm for the automatic refinement of the spectral characteristics of acoustic finite element models //Acoustical Physics. – 2016. – Ò. 62. – Ñ. 593-599. https://doi.org/10.1134/S1063771016050171

26. DeVore R. A., Temlyakov V. N. Some remarks on greedy algorithms //Advances in computational Mathematics. – 1996. – Ò. 5. – ¹. 1. – Ñ. 173-187. https://doi.org/10.1007/BF02124742

27. Dumitrescu B. Sparse total least squares: analysis and greedy algorithms //Linear Algebra and its Applications. – 2013. – Ò. 438. – ¹. 6. – Ñ. 2661-2674. https://doi.org/10.1016/j.laa.2012.10.032

 

For citation:

Kutuzov N.A., Rodionov A.A. Projection method for outlier detection in sensor data in vibroacoustics problems // Journal of Radio Electronics. – 2024. – ¹. 12. https://doi.org/10.30898/1684-1719.2024.12.8 (In Russian)