Physics Based and Data Driven Anomaly Detection Methods Using Vibration Data for Early Gear Damage Detection in Planetary Gearboxes
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
https://orcid.org/0000-0002-1730-0582
Martin Dazer
Abstract
Various methods are known for using vibration sensors to distinguish anomalies such as pitting damage from normal operating conditions in gear drives. These methods are capable of detecting severe damage. However, to take full advantage of prognostics and health management (PHM) strategies, it is necessary to detect damage in a very early damage state. The objective of this work is therefore to analyze, improve and expand the known data evaluation methods in order to achieve the earliest possible detection of gear pitting damage during operation. The research question is: What is the smallest detectable pitting size in planetary gears using vibration data, and which methods are best suited for detection? A high-resolution vibration data set from a single-stage helical planetary gearbox is available for this study. The vibrations were recorded at different speeds, torque levels, and sensor positions. The evaluation methods include entirely physicsbased methods in the frequency and time domain, especially a selective analysis of characteristic frequencies and sidebands. These methods are supplemented with data driven approaches such as similarity analysis of frequency spectra. In contrast to physics-based methods, data- riven approaches aim to detect deviations of data sets regardless of their origin. To exclude false positives, these approaches inevitably require the use of multiple measurements without damage as a reference. The application of these methods results in the calculation of 130 condition indicators (CIs). This study provides statistical evidence for the detectability of small damage sizes, particularly using data-driven methods. The key findings of the study are that most of the information about the damage is contained in a comparison of full spectra. A comparison of the full spectral range provides a much clearer picture of damage compared to the analysis of individual characteristic frequencies.
How to Cite
##plugins.themes.bootstrap3.article.details##
Planetary Gearbox, Damage Detection, Vibration, Condition Monitoring, Pitting
Bogert, B. P., Healy, M. J. R., & Tukey, J. W. (1963). The quefrency analysis of time series for echoes: Cepstrum, pseudo-autocovariance, cross-cepstrum and saphe cracking. In M. Rosenblatt (Ed.), Proceedings of the Symposium on Time Series Analysis (Chapter 15, pp. 209–243). Wiley.
Chaari, F., Fakhfakh, T., & Haddar, M. (2006). Dynamic analysis of a planetary gear failure caused by tooth pitting and cracking. Journal of Failure Analysis and Prevention, 6(2), 73–78. doi: 10.1361/154770206X99343
Cohen, J. (1988). Statistical power analysis for the behavioral sciences (2nd ed.). Routledge.
Farrar, C. R., & Doebling, S. W. (1999). Damage detection and evaluation II. In J. M. M. Silva & N. M. M. Maia (Eds.), Modal analysis and testing (pp. 345–378). Springer. doi: 10.1007/978-94-011-4503-9_17
Feng, Z., & Zuo, M. J. (2012). Vibration signal models for fault diagnosis of planetary gearboxes. Journal of Sound and Vibration, 331(22), 4919–4939. doi: 10.1016/j.jsv.2012.05.039
FVA Forschungvereinigung Antriebstechnik e.V., & Binanzer, L. (2026). FVA Heft 1698, FVA1036I: Sensorkonzept und Datenverarbeitung mittels künstlicher Intelligenz zur Frühsterkennung von Schäden und deren Lokalisation in Getriebeanwendungen. Frankfurt: Forschungsvereinigung Antriebstechnik e.V.
Gretzinger, Y., Kroner, A., Henß, M., Dazer, M., & Bertsche, B. (2021). Extended evaluation of pitting degradation tests to increase the remaining useful life of gear wheels. IOP Conference Series: Materials Science and Engineering, 1097(1), 012006. doi: 10.1088/1757-899X/1097/1/012006
Grzeszkowski, M., Gühmann, C., Scholzen, P., Löpenhaus, C., Nowoisky, S., & Kappmeyer, G. (2019). Experimental study on the pitting detection capabilities for spur gears using acoustic emission and vibration analysis methods. Gear Technology, March/April, 48–57.
Häderle, P., Merkle, L., & Dazer, M. (2024). Vibration analysis for early pitting detection during operation. Forschung im Ingenieurwesen, 88(1), 15. doi: 10.1007/s10010-024-00743-5
Hou, J., Yang, S., Li, Q., & Liu, Y. (2022). Effect of a novel tooth pitting model on mesh stiffness and vibration response of spur gears. Mathematics, 10(3), 471. doi: 10.3390/math10030471
Hu, C., Smith, W. A., Randall, R. B., & Peng, Z. (2016). Development of a gear vibration indicator and its application in gear wear monitoring. Mechanical Systems and Signal Processing, 76–77, 319–336. doi: 10.1016/j.ymssp.2016.01.018
Inalpolat, M., & Kahraman, A. (2009). A theoretical and experimental investigation of modulation sidebands of planetary gear sets. Journal of Sound and Vibration, 323(3–5), 677–696. doi: 10.1016/j.jsv.2009.01.004
ISO International Organization for Standardization. (2004). ISO 18431-2: Mechanical vibration and shock — Signal processing — Part 2: Time domain windows for Fourier transform analysis (ISO 18431-2:2004(E)).
ISO International Organization for Standardization. (2007). ISO 18431-4: Mechanical vibration and shock — Signal processing — Part 4: Shock-response spectrum analysis (ISO 18431-4:2007(E)).
ISO International Organization for Standardization. (2014). ISO 18431-3: Mechanical vibration and shock — Signal processing — Part 3: Methods of time-frequency analysis (ISO 18431-3:2014(E)).
ISO International Organization for Standardization. (2016). ISO 6336-5: Calculation of load capacity of spur and helical gears — Part 5: Strength and quality of materials (ISO 6336-5:2016(E)).
ISO International Organization for Standardization. (2020). ISO 20816-9: Mechanical vibration — Measurement and evaluation of machine vibration — Part 9: Gear units (ISO 20816-9:2020(E)).
Korka, Z. I., Bara, A., Clavac, B., & Filip, L. (2017). Gear pitting assessment using vibration signal analysis. Romanian Journal of Acoustics and Vibration, 14(1), 44–49.
Kundu, P., Darpe, A. K., & Kulkarni, M. S. (2019). A correlation coefficient-based vibration indicator for detecting natural pitting progression in spur gears. Mechanical Systems and Signal Processing, 129, 741–763. doi: 10.1016/j.ymssp.2019.04.058
Kundu, P., Darpe, A. K., & Kulkarni, M. S. (2020). An ensemble decision tree methodology for remaining useful life prediction of spur gears under natural pitting progression. Structural Health Monitoring, 19(3), 854–872. doi: 10.1177/1475921719865718
Kundu, P., Darpe, A. K., & Kulkarni, M. S. (2021). A review on diagnostic and prognostic approaches for gears. Structural Health Monitoring, 20(5), 2853–2893. doi: 10.1177/1475921720972926
Kuzio, D., Zimroz, R., & Wyłomańska, A. (2023). Identification of fault frequency variation in the envelope spectrum in vibration-based local damage detection under possible changing load/speed conditions. Measurement, 218, 113148. doi: 10.1016/j.measurement.2023.113148
Lebold, M., McClintic, K., Campbell, R., Byington, C., & Maynard, K. (2000). Review of vibration analysis methods for gearbox diagnostics and prognostics. In Proceedings of the 54th Meeting of the Society for Machinery Failure Prevention Technology (pp. 623–634). Applied Research Laboratory, The Pennsylvania State University.
Li, R., Xiong, X., Ma, J., & Zou, M. (2023). Effects of macro-pitting fault on dynamic characteristics of planetary gear train considering surface roughness. Actuators, 13(1), 1. doi: 10.3390/act13010001
Merkle, L., Binanzer, L., Häderle, P., & Dazer, M. (2024). Sensor concepts for gear damage detection in wind power drives. Journal of Physics, 2875, 012022. doi: 10.1088/1742-6596/2875/1/012022
Merkle, L., Binanzer, L., & Dazer, M. (2025). Gear damage detection in planetary gearboxes. In International Conference on Gears 2025. VDI Verlag GmbH. doi: 10.51202/9783181024607
Norton, M. P. (2003). Fundamentals of noise and vibration analysis for engineers (2nd ed.). Cambridge University Press.
Ozturk, H., Yesilyurt, I., & Sabuncu, M. (2010). Detection and advancement monitoring of distributed pitting failure in gears. Journal of Nondestructive Evaluation, 29(2), 63–73. doi: 10.1007/s10921-010-0066-4
Qu, Y., Zhang, Y., He, M., He, D., Jiao, C., & Zhou, Z. (2019). Gear pitting fault diagnosis using disentangled features from unsupervised deep learning. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 233(5), 719–730. doi: 10.1177/1748006X18822447
Randall, R. B. (2011). Vibration-based condition monitoring. John Wiley & Sons.
Rytter, A. (1993). Vibrational-based inspection of civil engineering structures [Unpublished doctoral dissertation, Aalborg University].
Sait, A. S., & Sharaf-Eldeen, Y. I. (2011). A review of gearbox condition monitoring based on vibration analysis techniques: Diagnostics and prognostics. In T. Proulx (Ed.), Rotating machinery, structural health monitoring, shock and vibration, Volume 5 (pp. 307–324). Springer. doi: 10.1007/978-1-4419-9428-8_25
Sánchez, R.-V., Lucero, P., Vásquez, R. E., Cerrada, M., & Cabrera, D. (2018). A comparative feature analysis for gear pitting level classification by using acoustic emission, vibration and current signals. IFAC-PapersOnLine, 51(24), 346–352. doi: 10.1016/j.ifacol.2018.09.600
Sarvestani, E. S., Rezaeizadeh, M., Jomehzadeh, E., & Bigani, A. (2020). Early detection of industrial-scale gear tooth surface pitting using vibration analysis. Journal of Failure Analysis and Prevention, 20(3), 768–788. doi: 10.1007/s11668-020-00874-1
Sendlbeck, S., Fromberger, M., Otto, M., & Stahl, K. (2021). Vibration-based gear condition monitoring using an improved section-specific approach without the need of historic reference data.
Teng, W., Wang, F., Zhang, K., Liu, Y., & Ding, X. (2014). Pitting fault detection of a wind turbine gearbox using empirical mode decomposition. Strojniški vestnik – Journal of Mechanical Engineering, 60(1), 12–20. doi: 10.5545/sv-jme.2013.1295
Tevetoglu, T., Henss, M., Gretzinger, Y., & Bertsche, B. (2021). Learning an optimal operational strategy for service life extension of gear wheels with double deep Q networks. Annual Conference of the PHM Society, 13(1). doi: 10.36001/phmconf.2021.v13i1.2978
The MathWorks, Inc. (2026). pwelch: Welch’s power spectral density estimate. MATLAB Help Center. Retrieved from https://de.mathworks.com/help/signal/ref/pwelch.html
Vishwakarma, M., Purohit, R., Harshlata, V., & Rajput, P. (2017). Vibration analysis and condition monitoring for rotating machines: A review. Materials Today: Proceedings, 4(2), 2659–2664. doi: 10.1016/j.matpr.2017.02.140
Welch, P. (1967). The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms. IEEE Transactions on Audio and Electroacoustics, 15(2), 70–73. doi: 10.1109/TAU.1967.1161901
Yakeu Happi, K. H., Kouejou, B. X. T., & Anyika Alugongo, A. (2023). Experimental study and comparative analysis of pitting fault in spur gear system. Journal of Vibroengineering, 25(8), 1480–1501. doi: 10.21595/jve.2023.23335
Zhe, C., Niaoqing, H., Fengshou, G., & Guojun, Q. (2011). Pitting damage levels estimation for planetary gear sets based on model simulation and grey relational analysis. Transactions of the Canadian Society for Mechanical Engineering, 35(3), 403–417. doi: 10.1139/tcsme-2011-0023
Zhu, R., Maele, D. V., Poletto, J. C., Baets, P. D., & Gryllias, K. (2024). Development and evaluation of vibration indicators for gear pitting detection. In International Conference on Noise and Vibration Engineering (ISMA 2024) and International Conference on Uncertainty in Structural Dynamics (USD 2024) (pp. 508–521). Katholieke Universiteit Leuven, Department of Mechanical Engineering.
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.