Vibro-acoustic signal analysis for lubrication regime identification in rolling element bearings using local mean decomposition

Vibro-acoustic signal analysis for lubrication regime identification in rolling element bearings using local mean decomposition

Deepak SHARMA, Rajendra Singh RAJPUT, Mukesh Kumar PANDEY, Shashikant PANDEY

Abstract. Rolling element bearings are the essential mechanical elements of rotating machines, whose operation is basically controlled by the existing lubrication conditions. In the current paper, a new vibro-acoustic signal-based model of detecting lubrication regimes in rolling element bearings based on Local Mean Decomposition (LMD) with statistical feature extraction and machine learning classification is introduced. Experimental data were obtained in a SKF NJ 307 ECP cylindrical roller bearing that is running at 800 rpm with a radial load of 2.1 kN, and in various lubrication conditions including boundary, mixed and hydrodynamic conditions. An accelerometer was attached to the bearing housing to sample the vibration signals at 20 kHz and an acoustic signal sampler was attached to a calibrated microphone at 40 kHz inside a semi-anechoic chamber. LMD was used to break down the acquired signals into Product Functions (PFs) based on which time-domain statistical measures such as Root Mean Square (RMS), kurtosis, crest factor, and entropy have been derived. The experimental findings demonstrate that the boundary lubrication generates impulsive and high-kurtosis signals, whereby the energy is concentrated on high-frequency PFs, whereas hydrodynamic lubrication is characterized by smooth and lower-kurtosis signals with the energy concentrated at lower frequencies. Acoustic signals were more sensitive to lubrication transitions than vibration signals and inter-class feature separability was better. The Support Vector Machine (SVM) and the Random Forest classifiers trained using LMD-derived features were able to discriminate between the three lubrication regimes. The suggested methodology provides a powerful non-invasive system of real-time lubrication conditions monitoring and predictive maintenance of bearing systems.

Keywords
Lubrication Regime, Rolling Element Bearing, Vibro-Acoustic Signals, Local Mean Decomposition, Feature Extraction, Condition Monitoring

Published online 8/15/2026, 8 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA

Citation: Deepak SHARMA, Rajendra Singh RAJPUT, Mukesh Kumar PANDEY, Shashikant PANDEY, Vibro-acoustic signal analysis for lubrication regime identification in rolling element bearings using local mean decomposition, Materials Research Proceedings, Vol. 71, pp 56-63, 2026

DOI: https://doi.org/10.21741/97816449042312-8

The article was published as article 8 of the book AI-Driven Innovations in Mechanical, Manufacturing, and Energy Engineering

Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.

References
[1] E.V. Zaretsky, E.V. Branzai, Rolling bearing service life based on probable cause for removal-a tutorial, Tribol. Trans. 60 (2017) 300-312. https://doi.org/10.1080/10402004.2016.1163761
[2] D. Dowson, G.R. Higginson, Elastohydrodynamic lubrication: The fundamentals of roller and gear lubrication, Pergamon Press, Oxford, 1966.
[3] R.B. Randall, J. Antoni, Rolling element bearing diagnostics-a tutorial, Mech. Syst. Signal Process. 25 (2011) 485-520. https://doi.org/10.1016/j.ymssp.2010.07.017
[4] J. Antoni, Cyclostationary by examples, Mech. Syst. Signal Process. 23 (2009) 987-1036. https://doi.org/10.1016/j.ymssp.2008.10.010
[5] M. Kalin, I. Velkavrh, J. Vižintin, The Stribeck curve and lubrication design for non-fully wetted surfaces, Wear 267 (2009) 1232-1240. https://doi.org/10.1016/j.wear.2008.12.072
[6] B. Wen, et al., Measurement and calculation of oil film thickness in a ball bearing, Ind. Lubr. Tribol. 70 (2018) 1500-1508. https://doi.org/10.1108/ILT-11-2016-0265
[7] A.M. Al-Ghamdi, D. Mba, A comparative experimental study on the use of acoustic emission and vibration analysis for bearing defect identification and estimation of defect size, Mech. Syst. Signal Process. 20 (2006) 1537-1571. https://doi.org/10.1016/j.ymssp.2004.10.013
[8] N. Tandon, G.S. Yadava, K.M. Ramakrishna, A comparison of some condition monitoring techniques for the detection of defect in induction motor ball bearings, Mech. Syst. Signal Process. 21 (2007) 244-256. https://doi.org/10.1016/j.ymssp.2005.08.005
[9] J. Hansen, et al., Robustness and sensitivity of the Λ*-ratio in microelastohydrodynamic lubrication, Tribol. Lett. 73 (2025) 129. https://doi.org/10.1007/s11249-025-02060-6
[10] F. Sadeghi, et al., A review of computational fluid dynamics approaches used to investigate lubrication of rolling element bearings, J. Tribol. 146 (2024) 100801. https://doi.org/10.1115/1.4065663
[11] T. Williams, et al., Rolling element bearing diagnostics in run-to-failure lifetime testing, Mech. Syst. Signal Process. 15 (2001) 979-993. https://doi.org/10.1006/mssp.2001.1418
[12] M.M. Maru, R.S. Castillo, L.R. Padovese, Study of solid contamination in ball bearings through vibration and wear analyses, Tribol. Int. 40 (2007) 433-440. https://doi.org/10.1016/j.triboint.2006.04.007
[13] T. Karacay, N. Akturk, Experimental diagnostics of ball bearings using statistical and spectral methods, Tribol. Int. 42 (2009) 836-843. https://doi.org/10.1016/j.triboint.2008.11.003
[14] B.P. Clarke, Development of ultrasonic techniques for rolling element bearing monitoring, Ph.D. thesis, University of Sheffield, 2022.
[15] J. Ren, et al., Study of the changes in the microstructures and properties of grease using ball milling to simulate a bearing shear zone on grease, Sci. Rep. 14 (2024) 9734. https://doi.org/10.1038/s41598-024-60399-7
[16] P.M. Cann, et al., Grease degradation in rolling element bearings, Tribol. Trans. 44 (2001) 399-404. https://doi.org/10.1080/10402000108982473
[17] N. Tandon, A. Choudhury, A review of vibration and acoustic measurement methods for the detection of defects in rolling element bearings, Tribol. Int. 32 (1999) 469-480. https://doi.org/10.1016/S0301-679X(99)00077-8
[18] N.E. Huang, Z. Shen, S.R. Long, M.C. Wu, H.H. Shih, Q. Zheng, N.C. Yen, C.C. Tung, H.H. Liu, The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, Proc. R. Soc. Lond. A 454 (1998) 903-995. https://doi.org/10.1098/rspa.1998.0193
[19] K. Kushwaha, P. Gupta, R. Mishra, Acoustic signal-based chatter detection in milling using variational mode decomposition and k-NN classifiers, Eng. Res. Express 8 (2026) 025407. https://doi.org/10.1088/2631-8695/ae35df
[20] J.S. Smith, The local mean decomposition and its application to EEG perception data, J. R. Soc. Interface 2 (2005) 443-454. https://doi.org/10.1098/rsif.2005.0058
[21] P. Gupta, B. Singh, Investigation of tool chatter using local mean decomposition and artificial neural network during turning of Al 6061, Soft Comput. 25 (2021) 11151-11174. https://doi.org/10.1007/s00500-021-05869-0