Classification of gear pitting damage using vibration measurements
-
Mateusz Grzeszkowski
Mateusz Grzeszkowski is currently a research assistant at the Chair of Electronic Measurement and Diagnostic Technology of the Technical University of Berlin with the emphasis on pattern recognition methods for the monitoring of spur gears and planetary gears. He has Bachelor and Master Degrees, both in Electrical Engineering. His experience in machine monitoring started during his master thesis, where he developed a diagnosis system for monitoring a rail wheelset axle using a non-destructive acoustic emission measurement technology. After graduating he started his research work with the topic on diagnosis methods for monitoring planetary gears at the Technical University of Berlin in cooperation with Rolls-Royce Germany.
,
Sebastian Nowoisky
Dr. Sebastian Nowoisky is currently PGB System Architect at Rolls-Royce Deutschland Ltd & Co KG working as R&T tech lead on the Power Gear Gearbox monitoring system. He earned his PHD at the TU Berlin in the field of mechatronic parameter identification of gearboxes in 2016. Before this time he work 5 years at the TU Berlin as researcher at the Chair of Electronic Measurement and Diagnostic Technology (MDT). In his professional experience of more than 11 years, he work as project engineer in the maintenance department at ThyssenKrupp. He get his Diploma Degree (Dipl.-Ing.) at the TU Berlin in 2008 after 2 years of studying electrical engineering with the specialization on measurement techniques. From 2002-2006 he studied electrical engineering at the University of applied science in Brandenburg achieving a degree as Dipl.-Ing (FH).
Philipp Scholzen M.Sc. is a research assistant and PhD student in the gear department at the Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University. He received his Bachelor degree (2014) and Master degree (2016) in Mechanical Engineering at RWTH Aachen University, specializing in automotive engineering. Today his main research topic is the operational behavior of powder metallurgical gears and the influence of gear body geometries, especially regarding NVH behavior.
Dr.-Ing. Gregor Kappmeyer is a Rolls-Royce Associate Engineering Fellow for Machining working on machining technologies for current and future Aero-Engine projects at Rolls-Royce. (2010-2011) He previously held positions as Chief of Commodity Rotatives and (2006-2009) Head of Manufacturing Engineering and Technology in Rolls-Royce Deutschland on machining R&T projects. (1999) He earnt his Doctorate in Manufacturing Engineering on ultrasonic assisted honing at the TU Braunschweig (1990 – 1997) following positions as team lead of the precision machining group and a researcher at the Institut für Werkzeugmaschinen und Fertigungstechnik (IWF) TU Braunschweig.
Prof. Clemens Gühmann has been a professor at the TU Berlin since 2003 where he heads the Chair of Electronic Measurement and Diagnostic Technology. His research interests are data-based and physical-based modelling, diagnostics, remaining useful lifetime prediction and control of mechatronic systems as well as measurement data processing.
Dr.-Ing. Jens Brimmers M.Sc. is the head of the gear department at the Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University since June 2019. He graduated from RWTH Aachen University with Master degrees in mechanical engineering and business administration. His PhD thesis focused on beveloid gears and topological tooth flank modifications.
Prof. Dr.-Ing. Christian Brecher has since January 2004 been Ordinary Professor for Machine Tools at the Laboratory for Machine Tools and Production Engineering (WZL) of the RWTH Aachen, as well as Director of the Department for Production Machines at the Fraunhofer Institute for Production Technology IPT. Upon finishing his academic studies in mechanical engineering, Brecher started his professional career first as a research assistant and later as team leader in the department for machine investigation and evaluation at the WZL. From 1999 to April 2001, he was responsible for the department of machine tools in his capacity as a Senior Engineer. After a short spell as a consultant in the aviation industry, Professor Brecher was appointed in August 2001 as the Director for Development at the DS Technologie Werkzeugmaschinenbau GmbH, Mönchengladbach, where he was responsible for construction and development until December 2003. Brecher has received numerous honors and awards, including the Springorum Commemorative Coin; the Borchers Medal of the RWTH Aachen; the Scholarship Award of the Association of German Tool Manufacturers (Verein Deutscher Werkzeugmaschinenfabriken VDW); and the Otto Kienzle Memorial Coin of the Scientific Society for Production Technology (Wissenschaftliche Gesellschaft für Produktionstechnik WGP).
Abstract
In future aero engines, a planetary gearbox is to be integrated between fan and turbine to increase the efficiency and bypass ratio. This gearbox has to be monitored during operation to detect possible gearbox faults such as gear wear or gear pitting at an early stage. This paper presents a method consisting of vibration measurement, sensor-dependent feature extraction and support-vector machine (SVM)-based classification of pitting for gear condition monitoring. Several gears were loaded with a constant torque on a standardized back-to-back test rig to provoke pitting, and the pitting amount was captured during the tests with a camera. Features are extracted from accelerometers and an acoustic emission sensor, and based on the results of the visually recorded pitting surface, SVM classification is applied to identify the pitting defect. In this contribution, two different SVM classification approaches are investigated. One approach uses a Two-Class SVM, where tests from one gearset are used for SVM training and another approach utilizes a One-Class SVM based on outlier detection. Both methods show that single tooth pitting defects with a relative pitting area of less than 1 % can be effectively identified, whereas the One-Class SVM method showed a higher pitting detection accuracy.
Zusammenfassung
In zukünftigen Flugtriebwerken soll ein Planetengetriebe zwischen Fan und Turbine integriert werden, um den Wirkungsgrad und das Nebenstromverhältnis des Triebwerks zu erhöhen. Ein solches Getriebe muss im fortlaufenden Betrieb überwacht werden, um mögliche Getriebeschäden wie Zahnradverschleiß oder Grübchen auf den Zahnradflanken frühzeitig zu erkennen. In diesem Beitrag wird eine Methode vorgestellt, die aus einer Schwingungsmessung, einer sensorabhängigen Merkmalsgewinnung und einer Support Vector Machine (SVM) zur Klassifikation von Zahnradgrübchen für die Zustandsüberwachung von Getrieben besteht. Mehrere Zahnräder wurden auf einem genormten Zahnrad-Verspannungsprüfstand mit einem konstanten Drehmoment bis zu einer vorgegebenen Grübchenfläche belastet. Die Grübchenfläche wurde versuchsbegleitend fotografisch erfasst. Es wurden Merkmale aus Beschleunigungssensoren und einem Körperschallsensor extrahiert. Auf der Grundlage der Ergebnisse der fotografisch erfassten Grübchenfläche wurde eine SVM-Klassifikation durchgeführt, um den Grübchenschaden zu identifizieren. In diesem Beitrag werden zwei verschiedene Klassifikationsansätze mittels SVM untersucht. Ein Ansatz verwendet eine Zwei-Klassen-SVM mit einem radsatzabhängigen Training der SVM und ein anderer Ansatz eine auf Ausreißererkennung basierende Ein-Klassen-SVM. Beide Methoden haben gezeigt, dass Grübchenschäden mit einer relativen Grübchenzahnfläche von weniger als 1 % effektiv identifiziert werden können, wohingegen mittels Ein-Klassen-SVM eine höhere Genauigkeit bei der Erkennung von Grübchenschäden erreicht werden konnte.
About the authors
Mateusz Grzeszkowski is currently a research assistant at the Chair of Electronic Measurement and Diagnostic Technology of the Technical University of Berlin with the emphasis on pattern recognition methods for the monitoring of spur gears and planetary gears. He has Bachelor and Master Degrees, both in Electrical Engineering. His experience in machine monitoring started during his master thesis, where he developed a diagnosis system for monitoring a rail wheelset axle using a non-destructive acoustic emission measurement technology. After graduating he started his research work with the topic on diagnosis methods for monitoring planetary gears at the Technical University of Berlin in cooperation with Rolls-Royce Germany.
Dr. Sebastian Nowoisky is currently PGB System Architect at Rolls-Royce Deutschland Ltd & Co KG working as R&T tech lead on the Power Gear Gearbox monitoring system. He earned his PHD at the TU Berlin in the field of mechatronic parameter identification of gearboxes in 2016. Before this time he work 5 years at the TU Berlin as researcher at the Chair of Electronic Measurement and Diagnostic Technology (MDT). In his professional experience of more than 11 years, he work as project engineer in the maintenance department at ThyssenKrupp. He get his Diploma Degree (Dipl.-Ing.) at the TU Berlin in 2008 after 2 years of studying electrical engineering with the specialization on measurement techniques. From 2002-2006 he studied electrical engineering at the University of applied science in Brandenburg achieving a degree as Dipl.-Ing (FH).
Philipp Scholzen M.Sc. is a research assistant and PhD student in the gear department at the Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University. He received his Bachelor degree (2014) and Master degree (2016) in Mechanical Engineering at RWTH Aachen University, specializing in automotive engineering. Today his main research topic is the operational behavior of powder metallurgical gears and the influence of gear body geometries, especially regarding NVH behavior.
Dr.-Ing. Gregor Kappmeyer is a Rolls-Royce Associate Engineering Fellow for Machining working on machining technologies for current and future Aero-Engine projects at Rolls-Royce. (2010-2011) He previously held positions as Chief of Commodity Rotatives and (2006-2009) Head of Manufacturing Engineering and Technology in Rolls-Royce Deutschland on machining R&T projects. (1999) He earnt his Doctorate in Manufacturing Engineering on ultrasonic assisted honing at the TU Braunschweig (1990 – 1997) following positions as team lead of the precision machining group and a researcher at the Institut für Werkzeugmaschinen und Fertigungstechnik (IWF) TU Braunschweig.
Prof. Clemens Gühmann has been a professor at the TU Berlin since 2003 where he heads the Chair of Electronic Measurement and Diagnostic Technology. His research interests are data-based and physical-based modelling, diagnostics, remaining useful lifetime prediction and control of mechatronic systems as well as measurement data processing.
Dr.-Ing. Jens Brimmers M.Sc. is the head of the gear department at the Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University since June 2019. He graduated from RWTH Aachen University with Master degrees in mechanical engineering and business administration. His PhD thesis focused on beveloid gears and topological tooth flank modifications.
Prof. Dr.-Ing. Christian Brecher has since January 2004 been Ordinary Professor for Machine Tools at the Laboratory for Machine Tools and Production Engineering (WZL) of the RWTH Aachen, as well as Director of the Department for Production Machines at the Fraunhofer Institute for Production Technology IPT. Upon finishing his academic studies in mechanical engineering, Brecher started his professional career first as a research assistant and later as team leader in the department for machine investigation and evaluation at the WZL. From 1999 to April 2001, he was responsible for the department of machine tools in his capacity as a Senior Engineer. After a short spell as a consultant in the aviation industry, Professor Brecher was appointed in August 2001 as the Director for Development at the DS Technologie Werkzeugmaschinenbau GmbH, Mönchengladbach, where he was responsible for construction and development until December 2003. Brecher has received numerous honors and awards, including the Springorum Commemorative Coin; the Borchers Medal of the RWTH Aachen; the Scholarship Award of the Association of German Tool Manufacturers (Verein Deutscher Werkzeugmaschinenfabriken VDW); and the Otto Kienzle Memorial Coin of the Scientific Society for Production Technology (Wissenschaftliche Gesellschaft für Produktionstechnik WGP).
References
1. H. M. Blanken, A. P. de Vries, H. E. Blok, and L. Feng. Multimedia Retrieval. Data-Centric Systems and Applications. Springer Berlin Heidelberg, 2007. ISBN 9783540728955.10.1007/978-3-540-72895-5Suche in Google Scholar
2. DIN Deutsches Institut für Normung e. V. DIN ISO 14635, Zahnräder – FZG-Prüfverfahren, Januar 2010.Suche in Google Scholar
3. EASA, European Environment Agency. European aviation environmental report 2019, 2019.Suche in Google Scholar
4. K. Fukunaga. Introduction to statistical pattern recognition. Computer science and scientific computing. Academic Press, San Diego, 2 ed. edition, 2009. ISBN 0-12-269851-7.Suche in Google Scholar
5. M. Grzeszkowski, C. Gühmann, P. Scholzen, C. Löpenhaus, S. Nowoisky, and G. Kappmeyer. Experimental Study on the Pitting Detection Capabilities for Spur Gears Using Acoustic Emission and Vibration Analysis Methods. In Gear Technology, volume 36, No. 2, pages 48–57. Randall Publications LLC, Elk Grove Village, Illinois, USA, 2019.Suche in Google Scholar
6. M. Grzeszkowski, S. Nowoisky, P. Scholzen, G. Kappmeyer, C. Gühmann, J. Brimmers, and C. Brecher. Klassifikation von Grübchenschäden an Zahnrädern mittels Vibrationsmessungen. tm – Technisches Messen, 87 (s1): s56–s61, 2020. ISSN 0171-8096. 10.1515/teme-2020-0026.Suche in Google Scholar
7. C. Louen, S. X. Ding, and C. Kandler, editors. A new Framework for Remaining Useful Life Estimation Using Support Vector Machine Classifier, [Piscataway, N.J.], 2013. IEEE.10.1109/SysTol.2013.6693833Suche in Google Scholar
8. C. J. Louen. Datenbasierte Zustandsüberwachung in Personenkraftfahrzeugen mit Anwendung an einem Drei-Wege-Katalysator. Springer Fachmedien Wiesbaden, Wiesbaden, 2016. ISBN 978-3-658-14444-9. 10.1007/978-3-658-14445-6.Suche in Google Scholar
9. R. Medina, M. Cerrada, D. Cabrera, R.-V. Sanchez, C. Li, and J. V. D. Oliveira. Deep Learning-Based Gear Pitting Severity Assessment Using Acoustic Emission, Vibration and Currents Signals. In 2019 Prognostics and System Health Management Conference (PHM-Paris), pages 210–216. IEEE, 2019. 02.05.2019 – 05.05.2019. ISBN 978-1-7281-0329-7. 10.1109/PHM-Paris.2019.00042.Suche in Google Scholar
10. Rolls-Royce. Rolls-Royce sets new aerospace record with UltraFanⓇ Power Gearbox, 2017. URL https://www.rolls-royce.com/media/our-stories/press-releases/2017/04-09-2017-rr-sets-new-aerospace-record-with-ultrafan-power-gearbox.aspx.Suche in Google Scholar
11. C. K. Tan, P. Irving, and D. Mba. A comparative experimental study on the diagnostic and prognostic capabilities of acoustics emission, vibration and spectrometric oil analysis for spur gears. Mechanical Systems and Signal Processing, 21 (1): 208–233, 2007. ISSN 08883270. 10.1016/j.ymssp.2005.09.015.Suche in Google Scholar
12. T. Tobie. Zur Grübchen- und Zahnfußtragfähigkeit einsatzgehärteter Zahnräder: Einflüsse aus Einsatzhärtungstiefe, Wärmebehandlung und Fertigung bei unterschiedlicher Baugröße. FZG, 2001.Suche in Google Scholar
13. T. Tobie and P. Matt. Empfehlungen zur Vereinheitlichung von Tragfähigkeitsversuchen an vergüteten und gehärteten Zylinderrädern. FVA-Richtlinie Nr. 563 I, 2012.Suche in Google Scholar
14. B. van den Heuvel. Schwingungstechnische Zustandsüberwachung von Antriebssträngen in Windenergieanlagen, 2015.Suche in Google Scholar
15. P. Vecer, M. Kreidl, and R. Smid. Condition Indicators for Gearbox Condition Monitoring Systems. Acta Polytechnica Vol. 45, No. 6/2005, pages 1–6, 2005. 10.1002/0471741833.ch1.Suche in Google Scholar
© 2021 Walter de Gruyter GmbH, Berlin/Boston
Artikel in diesem Heft
- Frontmatter
- Editorial
- XXXIV. Messtechnisches Symposium des AHMT
- Beiträge
- Analytical model for the signal-to-noise-ratio of drift tube ion mobility spectrometers
- Influence of input data representations for time-dependent instrument recognition
- Classification of gear pitting damage using vibration measurements
- Modelling damping in piezoceramics: A comparative study
- Monte Carlo method for the reduction of measurement errors in the material parameter estimation with cavities
- Microsphere-assisted interference microscopy for resolution enhancement
- Direct-imaging DOEs for high-NA multi-spot confocal surface measurement
Artikel in diesem Heft
- Frontmatter
- Editorial
- XXXIV. Messtechnisches Symposium des AHMT
- Beiträge
- Analytical model for the signal-to-noise-ratio of drift tube ion mobility spectrometers
- Influence of input data representations for time-dependent instrument recognition
- Classification of gear pitting damage using vibration measurements
- Modelling damping in piezoceramics: A comparative study
- Monte Carlo method for the reduction of measurement errors in the material parameter estimation with cavities
- Microsphere-assisted interference microscopy for resolution enhancement
- Direct-imaging DOEs for high-NA multi-spot confocal surface measurement
