Abstract
The paper is devoted to developing an innovative non-contact vibration measurement system for electrical equipment monitoring. A comprehensive comparative analysis of existing vibration monitoring methods is conducted, identifying their limitations and substantiating the necessity of transitioning to non-invasive diagnostic technologies for industrial unit predictive maintenance. To address the non-contact measurement challenge, high-speed imaging (≥1000 fps) of operating equipment is applied with subsequent frame-by-frame processing of reference points or areas displacement on the unit body. Technical limitations and equipment requirements are examined in detail including the necessity of satisfying Nyquist-Kotelnikov theorem for accurate high-frequency oscillation registration up to 500 Hz. For automatic detection and segmentation of target areas, identification using YOLOv4 neural network algorithms with CSPDarknet53 architecture trained via transfer learning on specialized industrial equipment dataset is proposed. The key point localization is performed using Shi-Tomasi corner detector with infrared fiducial markers support, ensuring sub-pixel positioning accuracy under variable illumination conditions. The acquired images undergo preprocessing for contrast enhancement using CLAHE method and noise suppression through cascaded Gaussian, median and bilateral filters. The system robustness to industrial operating conditions is achieved through synchronized pulsed IR illumination. Displacement tracking is performed by modified pyramidal Lucas-Kanade algorithm with inverse-compositional Gauss-Newton method providing metrological accuracy up to 0.01 pixel. Kinematic parameters calculation was performed using central differences method with subsequent Savitzky-Golay filtering. The vibration signal spectral analysis is implemented using fast Fourier transform and Morlet wavelet transform with preliminary adaptive Kalman filtering. The developed system demonstrates measurement error ≤5% in the 0-5 kHz range while achieving six-fold capital expenditure reduction as compared to laser vibrometers with two-year payback period.
Keywords
non-invasive vibration monitoring, technical vision, predictive maintenance, optical flow, YOLO, Lucas-Canade algorithm, spectral analysis
1. Dong C.Z., Celik O., Catbas F.N., O'Brien E.J., Taylor S. Structural displacement monitoring using deep learning-based full field optical flow methods. Struct. Infrastruct. Eng. 2020, vol. 16, pp. 51-71. doi: 10.1080/15732479.2019.1650078
2. Kalybek M., Bocian M., Nikitas N. Performance of Optical Structural Vibration Monitoring Systems in Experimental Modal Analysis. Sensors. 2021, vol. 21, 1239. doi: 10.3390/s21041239
3. Chen X., Ling J., Wang S., Yang Y., Luo L., Yan Y. Ship detection from coastal surveillance videos via an ensemble Canny-Gaussian-morphology framework. The Journal of Navigation. 2021, vol. 74, pp. 1252-1266. doi: 10.1017/ S0373463321000540
4. Lucas B.D., Kanade T. An Iterative Image Registration Technique with an Application to Stereo Vision. Proc. DARPA Image Understanding Workshop. Vancouver, BC, Canada, 24-28 August 1981. 1981. Pp. 121-130.
5. Zhang G., Li H., Shen S., Trinh T., He F., Talke F.E. Effect of Track-Seeking Motion on Off-Track Vibrations of the Head-Gimbal Assembly in HDDs. IEEE Trans. Magn. 2018, vol. 54, pp. 1-6. doi: 10.1109/TMAG.2018.2804918
6. Dong C.Z., Bas S., Catbas F.N. Investigation of vibration serviceability of a footbridge using computer vision-based methods. Eng. Struct. 2020, vol. 224, 111224. doi: 10.1016/ j.engstruct.2020.111224
7. Khuc T., Catbas F.N. Computer vision-based displacement and vibration monitoring without using physical target on structures. Struct. Infrastruct. Eng. 2017, vol. 13, pp. 505-516. doi: 10.1080/15732479.2016.1164729
8. Choi H., Kang B., Kim D. Moving Object Tracking Based on Sparse Optical Flow with Moving Window and Target Estimator. Sensors. 2022, vol. 22(8), 2878. doi: 10.3390/ s22082878
9. Xu Y., Brownjohn J.M. Review of machine-vision based methodologies for displacement measurement in civil structures. J. Civ. Struct. Health Monit. 2018, vol. 8, pp. 91-110. doi: 10.1007/s13349-017-0261-4
10. Khaloo A., Lattanzi D. Pixel-wise structural motion tracking from rectified repurposed videos. Struct. Control Health Monit. 2017, vol. 24 (11), 2009. doi: 10.1002/stc.2009
11. Kalybek M., Bocian M., Pakos W., Grosel J., Nikitas N. Performance of Camera-Based Vibration Monitoring Systems in Input-Output Modal Identification Using Shaker Excitation Remote Sens. 2021, vol. 13(17), 3471. doi: 10.3390/rs13173471
12. Hosseinzadeh A.Z., Harvey P., Jr. Pixel-based operating modes from surveillance videos for structural vibration monitoring: A preliminary experimental study. Measurement. 2019, vol. 148, 106911. doi: 10.1016/j.measurement. 2019.106911
13. Lydon D., Lydon M., Taylor S., Del Rincon J.M., Hester D., Brownjohn J. Development and field testing of a vision-based displacement system using a low cost wireless action camera. Mech. Syst. Signal Process. 2019, vol. 121, pp. 343-358. doi: 10.1016/j.ymssp.2018.11.015
14. Yoon H., Elanwar H., Choi H., Golparvar-Fard M., Spencer B.F., Jr. Target-free approach for vision-based structural system identification using consumer-grade cameras. Struct. Control Health Monit. 2016, vol. 23, pp. 1405-1416. doi: 10.1002/stc.1850
15. Dong C.Z., Celik O., Catbas F.N. Marker-free monitoring of the grandstand structures and modal identification using computer vision methods. Struct. Health Monit. 2019, vol. 18, pp. 1491-1509. doi: 10.1177/1475921718806895
16. Song Y.Z., Bowen C.R., Kim A.H., Nassehi A., Padget J., Gathercole N. Virtual visual sensors and their application in structural health monitoring. Struct. Health Monit. 2014, vol. 13, pp. 251-264. doi: 10.1177/1475921714522841
17. Horn B.K., Schunck B.G. Determining optical flow. Artif. Intell. 1981, vol. 17, pp. 185-203. doi: 10.1016/0004-3702(81)90024-2
18. Black M.J., Anandan P. The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields. Comput. Vis. Image Underst. 1996, vol. 63, pp. 75-104. doi: 10.1006/cviu.1996.0006
19. Sun D., Roth S., Black M.J. Secrets of optical flow estimation and their principles. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. IEEE, 2010, pp. 2432-2439. doi: 10.1109/CVPR.2010.5539939
20. Farneback G. Very high accuracy velocity estimation using orientation tensors, parametric motion, and simultaneous segmentation of the motion field. Proc. 8th IEEE Int. Conf. Comput. Vis. (ICCV 2001). IEEE, 2001, vol. 1, pp. 171-177. doi: 10.1109/ICCV.2001.937514
21. Farneback G. Fast and accurate motion estimation using orientation tensors and parametric motion models. Proc. 15th Int. Conf. Pattern Recognit. (ICPR-2000). IEEE, 2000, vol. 1, pp. 135-139. doi: 10.1109/ICPR.2000.905291
22. Farnebäck G. Two-frame motion estimation based on polynomial expansion. Scand. Conf. Image Anal. Berlin/Heidelberg, Germany: Springer, 2003, pp. 363-370. doi: 10.1007/3-540-45103-X_50
23. Won J., Park J.W., Park K., Yoon H., Moon D.S. Non-target structural displacement measurement using reference frame-based deepflow. Sensors. 2019, vol. 19, 2992. doi: 10.3390/s19132992
24. Guo J. Dynamic displacement measurement of large-scale structures based on the Lucas-Kanade template tracking algorithm. Mech. Syst. Signal Process. 2016, vol. 66, pp. 425-436. doi: 10.1016/j.ymssp.2015.06.004
25. Xu Y., Brownjohn J.M., Huseynov F. Accurate deformation monitoring on bridge structures using a cost-effective sensing system combined with a camera and accelerometers: Case study. J. Bridge Eng. 2019, vol. 24, 05018014. doi: 10.1061/ (ASCE)BE.1943-5592.0001330
26. Xu Y., Brownjohn J., Hester D., Koo K. Dynamic displacement measurement of a long span bridge using vision-based system. Proc. 8th European Workshop on Structural Health Monitoring (EWSHM). Bilbao, Spain, 5-8 July 2016. 2016.
27. Ilg E., Mayer N., Saikia T., Keuper M., Dosovitskiy A., Brox T. Flownet 2.0: Evolution of optical flow estimation with deep networks. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Honolulu, HI, USA, 21-26 July 2017. 2017, pp. 2462-2470. doi: 10.48550/arXiv.1612.01925
28. Liu B., Zhang D., Guo J., Zhu C. Vision-based displacement measurement sensor using modified Taylor approximation approach. Opt. Eng. 2016, vol. 55, 114103. doi: 10.1117/1. OE.55.11.114103
29. Weinzaepfel P., Revaud J., Harchaoui Z., Schmid C. DeepFlow: Large displacement optical flow with deep matching. Proc. IEEE Int. Conf. Comput. Vis. IEEE, 2013, pp. 1385-1392. doi: 10.1109/ICCV.2013.175
30. Omidalizarandi M., Kargoll B., Paffenholz J.A., Neumann I. Accurate vision-based displacement and vibration analysis of bridge structures by means of an image-assisted total station. Adv. Mech. Eng. 2018, vol. 10, 1687814018780052. doi: 10.1177/1687814018780052
31. Zhong J., Zhong S., Zhang Q., Zhuang Y., Lu H., Fu X. Vision-based measurement system for structural vibration monitoring using non-projection quasi-interferogram fringe density enhanced by spectrum correction method. Meas. Sci. Technol. 2016, vol. 28, 015903. doi: 10.1088/1361-6501/28/1/015903
32. Alipour M., Washlesky S.J., Harris D.K. Field deployment and laboratory evaluation of 2D digital image correlation for deflection sensing in complex environments. J. Bridge Eng. 2019, vol. 24, 04019010.
33. Harmanci Y.E., Gülan U., Holzner M., Chatzi E. A novel approach for 3D-structural identification through video recording: Magnified tracking. Sensors. 2019, vol. 19, 1229. doi: 10.3390/s19051229
Meshcheryakov V.N., Kazakov M.Yu., Kondratyev S.E. Development of a non-invasive vibration monitoring system for electrical equipment using technical vision. Elektrotekhnicheskie sistemy i kompleksy [Electrotechnical Systems and Complexes], 2025, no. 4(69), pp. 61-70. (In Russian). https://doi.org/10.18503/2311-8318-2025-4(69)-61-70