Damage Detection using Machine Learning for PHM in Gearbox Applications

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jun 27, 2024
Lisa Binanzer Tobias Schmid Lukas Merkle Martin Dazer

Abstract

Early damage detection in gearbox applications enables the implementation of Prognostics and Health Management (PHM). On the one hand, the earliest possible damage detection provides a precise in-sight into the state of health of a gearbox. In addition, early damage detection offers the possibility to slow down the damage progress and extend the remaining useful life (RUL) by intervening in the operating state at an early damage stage. The main contribution of this work is that existing Machine Learning tools are applied to the challenge of very early damage detection in gearboxes. Thus, the need for complex physically based data evaluation is avoided. The aim of this investigation is a comparison of two different machine learning approaches. To investigate the detection possibilities test bench experiments were conducted with a single stage spur gearbox. For a comprehensive investigation, i.e. to detect damage under different operating conditions, the test runs are carried out at different damage sizes, speeds and torques. Based on the recorded vibration data, the damage detection is examined. Two machine learning approaches of anomaly detection are considered: An encoding approach and a loss approach. The same sparse autoencoder is developed for both approaches Both machine learning approaches are able to detect even the smallest damage of about 0.5 % in most operating states. The loss approach allows the different damage stages to be recognized much more clearly than the encoding approach. The comparison of the different approaches provides valuable insights for the further development of robust damage detection algorithms.

How to Cite

Binanzer, L., Schmid, T., Merkle, L., & Dazer, M. (2024). Damage Detection using Machine Learning for PHM in Gearbox Applications. PHM Society European Conference, 8(1), 12. https://doi.org/10.36001/phme.2024.v8i1.4062
Abstract 225 | PDF Downloads 139

##plugins.themes.bootstrap3.article.details##

Keywords

Damage Detection, Machine Learning, Gear Damage, Autoencoder

References
Bertsche, B. & Dazer, M. (2022). Zuverlässigkeit im Fahrzeug- und Maschinenbau: Ermittlung von Bauteil- und System-Zuverlässigkeiten. Berlin, Heidelberg: Springer Berlin Heidelberg. Binanzer, L., Merkle, L., Dazer, M. & Nicola, A. (2023). Pitting Detection for Prognostics and Health Management in Gearbox Applications. International Conference on Gears 2023 (VDI-Berichte, vol. 2422, pp. 97-108), September 13-15, Munich, Germany. doi:10.51202/9783181024225 Fan, Q., Zhou, Q., Wu, C. & Guo, M. (2017). Gear tooth surface damage diagnosis based on analyzing the vibration signal of an individual gear tooth. Advances in Mechanical Engineering (AIME), vol. 9 (no. 6), pp. 1-14. doi: 10.1177/1687814017704356 German Institute for Standardization (DIN) (2010). Industrial liquid lubricants - ISO viscosity classification (ISO 3448:1992). In DIN, DIN ISO 3448:2010-02. Berlin, Germany: Beuth Verlag GmbH. doi: 10.31030/1562009 Goebel, K., Celaya, J., Sankararaman, S., Roychoudhury, I., Daigle, M. & Abhinav, S. (2017) Prognostics: The Science of Making Predictions. CreateSpace Independent Publishing Platform. Gretzinger, Y., Lucan, K., Stoll, C., & Bertsche, B. (2020). Lifetime Extension of Gear Wheels using an Adaptive Operating Strategy. Proceedings of 7th International Conference Integrity-Reliability-Failure (pp. 703-710), September 6-10, Funchal, Portugal. https://fe.up.pt/irf/Proceedings_IRF2020/

Grzeszkowski, M., Nowoisky, S., Scholzen, P., Kappmeyer, G., Gühmann, C., Brimmers, J. & Brecher, C. (2020). Classification of Gear Pitting Severity Levels using Vibration Measurements. In tm - Technisches Messen, vol. 87 (no. s1), pp. s56-s61. doi: 10.1515/teme-2020-0026 Häderle, P., Merkle, L. & Dazer, M. (2024). Vibration Analysis for Early Pitting Detection During Operation. Forschung im Ingenieurwesen. vol. 88 (article nr. 15). doi:

10.1007/s10010-024-00743-5

Institute of Electrical and Electronics Engineers (IEEE) (2017). IEEE Standard Framework for Prognostics and Health Management of Electronic Systems. In IEEE, IEEE Std 1856-2017 (pp. 1-31). doi: 10.1109/IEEESTD.2017.8227036 International Organization for Standardization (ISO) (2016). Calculation of load capacity of spur and helical gears Part 5: Strength and quality of materials. In ISO, ISO6336-5:2016(E), (p. 5). Genève, Switzerland: International Standards Organization. Medina, R., Cerrada, M., Cabrera, D., Sanchez, R.-V., Li, C. & Oliveira, J. V. D. (2019). Deep Learning-Based Gear Pitting Severity Assessment Using Acoustic Emission, Vibration and Currents Signals. Proceedings of 2019 Prognostics and System Health Management Conference (PHM-Paris 2019) (pp. 210-216), May 2-5, Paris, France. doi: 10.1109/PHM-Paris.2019.00042 Ng, A. (2011). Sparse autoencoder. CS294A Lecture notes, 72, pp. 1-19. Qu, Y., He, M., Deutsch, J. & He, D. (2017). Detection of Pitting in Gears Using a Deep Sparse Autoencoder. Applied Science. Special Issue Deep Learning Based Machine Fault Diagnosis and Prognosis, vol. 7 (no. 5), pp. 515-529. doi: 10.3390/app7050515 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, vol. 233 (no. 5), pp. 719-730. doi:

10.1177/1748006X18822447

Research Association for Drive Technology (FVA) (1985).

FVA-Heft 180 Referenzöle - Datensammlung für Mineralöle.

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 Preventionm, vol. 20, pp. 768-

788. doi: 10.1007/s11668-020-00874-1

Sonawane, P. R. & Chandrasekaran, M. (2020). Investigation of gear pitting defect using vibration characteristics in a single-stage gearbox. The International Journal of Electrical Engineering & Education, vol. 57 (no. 3). doi:

10.1177/0020720918813837
Section
Technical Papers