EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Vibration-Based Wear Condition Estimation of Journal Bearings Using Convolutional Autoencoders

Cihan Ates iD, Tobias Höfchen, Mario Witt, Rainer Koch, Hans-Jörg Bauer iD

Sensors · 16.11.2023 · 23 (22) · 9212

DOI: 10.3390/s23229212 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 16.11.2023. Verfasst von Cihan Ates und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Thermal Turbomachinery, Karlsruhe Institute of Technology (KIT), 76137 Karlsruhe, Germany. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predictive maintenance is considered a proactive approach that capitalizes on advanced sensing technologies and data analytics to anticipate potential equipment malfunctions, enabling cost savings and improved operational efficiency. For journal bearings, predictive maintenance assumes critical significance due to the inherent complexity and vital role of these components in mechanical systems. The primary objective of this study is to develop a data-driven methodology for indirectly determining the wear condition by leveraging experimentally collected vibration data. To accomplish this goal, a novel experimental procedure was devised to expedite wear formation on journal bearings. Seventeen bearings were tested and the collected sensor data were employed to evaluate the predictive capabilities of various sensors and mounting configurations. The effects of different downsampling methods and sampling rates on the sensor data were also explored within the framework of feature engineering. The downsampled sensor data were further processed using convolutional autoencoders (CAEs) to extract a latent state vector, which was found to exhibit a strong correlation with the wear state of the bearing. Remarkably, the CAE, trained on unlabeled measurements, demonstrated an impressive performance in wear estimation, achieving an average Pearson coefficient of 91% in four different experimental configurations. In essence, the proposed methodology facilitated an accurate estimation of the wear of the journal bearings, even when working with a limited amount of labeled data.

Schlagwörter

Stichwörter der Autor:innen

convolutionconvolutional autoencoderjournal bearingsmachine learningstate space modelingstate trajectoryunsupervised learningvibration sensors

Autor:innen und Institutionen

  • Institute of Thermal Turbomachinery, Karlsruhe Institute of Technology (KIT), 76137 Karlsruhe, Germany.
  • Rheinmetall AG, Business Unit Bearings, KS Gleitlager GmbH, 68789 Sankt Leon-Rot, Germany.

ORCID-Profile: Cihan Ates, Hans-Jörg Bauer

Zitieren

APA

Ates, C., Höfchen, T., Witt, M., Koch, R., & Bauer, H. J. (2023). Vibration-Based Wear Condition Estimation of Journal Bearings Using Convolutional Autoencoders. Sensors, 23(22), 9212. https://doi.org/10.3390/s23229212

Vancouver

Ates C, Höfchen T, Witt M, Koch R, Bauer HJ. Vibration-Based Wear Condition Estimation of Journal Bearings Using Convolutional Autoencoders. Sensors. 2023;23(22):9212. doi:10.3390/s23229212

BibTeX
@article{Ates2023,
  author = {Ates, Cihan and Höfchen, Tobias and Witt, Mario and Koch, Rainer and Bauer, Hans-Jörg},
  title = {Vibration-Based Wear Condition Estimation of Journal Bearings Using Convolutional Autoencoders},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {22},
  pages = {9212},
  doi = {10.3390/s23229212}
}
Kostenlos starten →