Wear volume estimation for a journal bearing dataset
-
José-Luis Bote-Garcia
M. Sc. José-Luis Bote-Garcia studied electrical engineering and computer science at the University of Applied Sciences of Aschaffenburg. During this time, he was in Mumbai via the DAAD (RISE Worldwide) for a research internship. Afterward, he completed a Master in Electrical Engineering at the Technical University of Berlin focused on automation technology. At this time, he worked as a student assistant on the research project CargoCBM. After a stay abroad in Valencia, he finished his studies with a master thesis at Harting KGaA in Berlin. He then started working as a research assistant at the TU Berlin. Since 2015, he has been employed at the Chair Electronic Measurement and Diagnostic Technology. He supervises lectures on measurement data processing and modeling of technical systems. His research focuses on predicting the remaining useful lifetime on the example of journal bearings using machine learning.
and
Clemens Gühmann
Prof. Dr.-Ing. Clemens Gühmann studied electrical engineering and has been head of the Chair Electronic Measurement and Diagnostic Technology since 2003 at the Technische Universität Berlin. His areas of expertise include measurement technology and data processing and the diagnosis, modeling, simulation and automatic control of mechatronic systems.
Abstract
To develop a system for predicting the remaining useful lifetime of a journal bearing, it is necessary to monitor the progressive wear quantitatively. For this purpose, we create a dataset where the wear volume is tracked throughout several experiments. The roundness profile is used to determine the wear volume over the entire life of the journal bearing. Therefore, a procedure for tracking the wear volume is described. The uncertainty of the procedure is analyzed. It is shown that the procedure has good accuracy and that the uncertainty is induced by the manual setting of the measuring positions. It has been shown that acoustic emission can be used to classify different friction states and identify defects in journal bearings. In addition, it has been demonstrated in experimental setups that it can be used to estimate the wear volume of sliding lubricated metallic contacts. Several experiments were carried out under different operating conditions for the dataset’s creation. Finally, the root mean square value of the acquired acoustic emission signal is used for estimation. Linear regression, random forest regressor, multilayer perceptron, and recurrent neuronal network are applied. The wear volume can be estimated with a root mean square error of 0.32 mm3 and a coefficient of determination of 93 %. Neural networks have the distinct advantage of being able to estimate wear at any point during an experiment.
Zusammenfassung
Um ein System zur Vorhersage der Restlebensdauer eines Gleitlagers zu entwickeln, ist es notwendig, den fortschreitenden Verschleiß quantitativ zu überwachen. Zur Entwicklung eines solchen Systems wird ein Datensatz erstellt, in dem das Verschleißvolumen über mehrere Versuche hinweg erfasst wird. Das Rundheitsprofil kann zur Ermittlung des Verschleißvolumens über die gesamte Lebensdauer des Gleitlagers verwendet werden. Hierzu wird ein Verfahren zur Abschätzung des Verschleißvolumens beschrieben. Die Unsicherheit des Verfahrens wird analysiert, wobei gezeigt wird, dass das Verfahren eine gute Genauigkeit aufweist und dass die Unsicherheit durch die manuelle Einstellung der Messpositionen bedingt ist. In vorhergehenden Arbieten wurde gezeigt, dass der Körperschall zur Klassifizierung verschiedener Reibungszustände und zur Identifizierung von Defekten in Gleitlagern verwendet werden kann. Darüber hinaus wurde über Versuchsaufbauten gezeigt, dass es zur Schätzung des Verschleißvolumens gleitgeschmierter metallischer Kontakte verwendet werden kann. Für die Erstellung des Datensatzes wurden mehrere Experimente unter verschiedenen Betriebsbedingungen durchgeführt. Letztendlich wird der quadratische Mittelwert des erfassten Köperschallsignals für eine Schätzung verwendet. Dabei werden eine lineare Regression, Random-Forest-Regressor, Multilayer Perceptron und ein Rekurrentes Neuronales Netz verwendet. Das Verschleißvolumen kann mit einem mittleren quadratischen Fehler von 0.64 mm3 und einem Bestimmtheitsmaß 93 % vorhergesagt werden. Die Neuronalen Netze haben den entscheidenen Vorteil, dass sie den Verschleiß zu jedem Zeitpunk während eines Experiments schätzen können.
About the authors
M. Sc. José-Luis Bote-Garcia studied electrical engineering and computer science at the University of Applied Sciences of Aschaffenburg. During this time, he was in Mumbai via the DAAD (RISE Worldwide) for a research internship. Afterward, he completed a Master in Electrical Engineering at the Technical University of Berlin focused on automation technology. At this time, he worked as a student assistant on the research project CargoCBM. After a stay abroad in Valencia, he finished his studies with a master thesis at Harting KGaA in Berlin. He then started working as a research assistant at the TU Berlin. Since 2015, he has been employed at the Chair Electronic Measurement and Diagnostic Technology. He supervises lectures on measurement data processing and modeling of technical systems. His research focuses on predicting the remaining useful lifetime on the example of journal bearings using machine learning.
Prof. Dr.-Ing. Clemens Gühmann studied electrical engineering and has been head of the Chair Electronic Measurement and Diagnostic Technology since 2003 at the Technische Universität Berlin. His areas of expertise include measurement technology and data processing and the diagnosis, modeling, simulation and automatic control of mechatronic systems.
References
1. DIN EN ISO 4287, 2010.Search in Google Scholar
2. SURFCOM TOUCH Series. ACCRETECH, 2021. URL https://metrology.accretech.eu/surfcom-touch-serie-de.Search in Google Scholar
3. A. Albers and M. Dickerhof. Simultaneous monitoring of rolling-element and journal bearings using analysis of structure-born ultrasound acoustic emissions. In ASME International Mechanical Engineering Congress and Exposition, volume 44502, pages 247–255, 2010.10.1115/IMECE2010-39814Search in Google Scholar
4. A. Albers, W. Burger, R. Scovino, and M. Dickerhof. Monitoring lubrication regimes in sliding bearings using acoustic emission analysis. Practicing Oil Analysis, 9(3):8–12, 2006.Search in Google Scholar
5. R. Boness and S. McBride. Adhesive and abrasive wear studies using acoustic emission techniques. Wear, 149(1-2):41–53, 1991.10.1016/0043-1648(91)90363-YSearch in Google Scholar
6. R. Boness, S. McBride, and M. Sobczyk. Wear studies using acoustic emission techniques. Tribology International, 23(5):291–295, 1990.10.1016/0301-679X(90)90001-6Search in Google Scholar
7. J.-L. Bote-Garcia and C. Gühmann. Journal bearing acoustic emission wear dataset, 2021. URL https://dx.doi.org/10.21227/fy48-ew50.Search in Google Scholar
8. J.-L. Bote-Garcia, N. Mokhtari, and C. Gühmann. Wear monitoring of journal bearings with acoustic emission under different operating conditions. In PHM Society European Conference, volume 5, page 8, 2020.10.36001/phme.2020.v5i1.1202Search in Google Scholar
9. L. Breiman. Random forests. Machine learning, 45(1):5–32, 2001.10.1023/A:1010933404324Search in Google Scholar
10. J. L. F. Chacon, E. A. Andicoberry, V. Kappatos, G. Asfis, T.-H. Gan, and W. Balachandran. Shaft angular misalignment detection using acoustic emission. Applied acoustics, 85:12–22, 2014.10.1016/j.apacoust.2014.03.018Search in Google Scholar
11. K. Cho, B. Van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio. Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078, 2014.10.3115/v1/D14-1179Search in Google Scholar
12. L. D. Hall and D. Mba. Diagnosis of continuous rotor-stator rubbing in large scale turbine units using acoustic emissions. Ultrasonics, 41(9):765–773, 2004.10.1016/j.ultras.2003.09.002Search in Google Scholar
13. A. Hase, H. Mishina, and M. Wada. Correlation between features of acoustic emission signals and mechanical wear mechanisms. Wear, 292:144–150, 2012.10.1016/j.wear.2012.05.019Search in Google Scholar
14. A. Hase, H. Mishina, and M. Wada. Fundamental study on early detection of seizure in journal bearing by using acoustic emission technique. Wear, 346:132–139, 2016.10.1016/j.wear.2015.11.012Search in Google Scholar
15. F. König, J. Marheineke, G. Jacobs, C. Sous, M. J. Zuo, and Z. Tian. Data-driven wear monitoring for sliding bearings using acoustic emission signals and long short-term memory neural networks. Wear, 476(3):203616, 2021a.10.1016/j.wear.2021.203616Search in Google Scholar
16. F. König, C. Sous, A. O. Chaib, and G. Jacobs. Machine learning based anomaly detection and classification of acoustic emission events for wear monitoring in sliding bearing systems. Tribology International, 155:106811, 2021b.10.1016/j.triboint.2020.106811Search in Google Scholar
17. M. Leahy, D. Mba, P. Cooper, A. Montgomery, and D. Owen. Experimental investigation into the capabilities of acoustic emission for the detection of shaft-to-seal rubbing in large power generation turbines: a case study. Proceedings of the Institution of Mechanical Engineers, Part J: Journal of Engineering Tribology, 220(7):607–615, 2006.10.1243/13506501JET170Search in Google Scholar
18. L. Li, K. Jamieson, A. Rostamizadeh, E. Gonina, J. Ben-Tzur, M. Hardt, B. Recht, and A. Talwalkar. A system for massively parallel hyperparameter tuning. Proceedings of Machine Learning and Systems, 2:230–246, 2020.Search in Google Scholar
19. Y. Li and W. Cheng. An online monitoring system of friction fault based on acoustic emission technology. In 2009 2nd International Conference on Power Electronics and Intelligent Transportation System (PEITS), volume 1, pages 329–332. IEEE, 2009.10.1109/PEITS.2009.5407005Search in Google Scholar
20. N. Mokhtari, R. Knoblich, S. Nowoisky, J.-L. Bote-Garcia, and C. Gühmann. Differentiation of journal bearing friction states under varying oil viscosities based on acoustic emission signals. In 2019 IEEE International Conference on Prognostics and Health Management (ICPHM), pages 1–7, 2019.10.1109/ICPHM.2019.8819371Search in Google Scholar
21. N. Mokhtari, J. G. Pelham, S. Nowoisky, J.-L. Bote-Garcia, and C. Gühmann. Friction and Wear Monitoring Methods for Journal Bearings of Geared Turbofans Based on Acoustic Emission Signals and Machine Learning. Lubricants, 8(3):29, 2020.10.3390/lubricants8030029Search in Google Scholar
22. S. C. Sharma and D. Hargreaves. A suitable method for journal bearing wear measurement. Industrial lubrication and tribology, 66(1):15–22, 2014.10.1108/ILT-06-2011-0104Search in Google Scholar
23. Oberflächen-, Kontur- und Formmessgeräte. ZEISS, 2021. URL https://www.zeiss.de/messtechnik/broschueren.html?catalog=rondcom.Search in Google Scholar
© 2022 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Editorial
- XXXV. Messtechnisches Symposium des AHMT
- Beiträge
- Funktionsprinzip und Anwendung der Kraftkompensationsmessmethode für miniaturisierte hydrogelbasierte Sensoren
- Auslegung neuartiger Transferkörper für die Kalibrierung von Massenormalen
- Lamb wave based approach to the determination of acoustic material parameters
- Metrological nanopositioning combined with two-photon direct laser writing
- Investigation of measurement data of low-coherence interferometry at tilted surfaces in the 3D spatial frequency domain
- Erfassung der Schmelzbadfläche mit Korrektur der Perspektive zur Prozessregelung eines Wire and Arc Additive Manufacturing
- Wear volume estimation for a journal bearing dataset
- Scalable multi-distance measurement approach for the optical assessment of tooth-individual shape parameters of large gearings
Articles in the same Issue
- Frontmatter
- Editorial
- XXXV. Messtechnisches Symposium des AHMT
- Beiträge
- Funktionsprinzip und Anwendung der Kraftkompensationsmessmethode für miniaturisierte hydrogelbasierte Sensoren
- Auslegung neuartiger Transferkörper für die Kalibrierung von Massenormalen
- Lamb wave based approach to the determination of acoustic material parameters
- Metrological nanopositioning combined with two-photon direct laser writing
- Investigation of measurement data of low-coherence interferometry at tilted surfaces in the 3D spatial frequency domain
- Erfassung der Schmelzbadfläche mit Korrektur der Perspektive zur Prozessregelung eines Wire and Arc Additive Manufacturing
- Wear volume estimation for a journal bearing dataset
- Scalable multi-distance measurement approach for the optical assessment of tooth-individual shape parameters of large gearings
