EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Anomaly Detection and Remaining Useful Life Estimation for the Health and Usage Monitoring Systems 2023 Data Challenge

Omri Matania iD, Eric Bechhoefer iD, David Blunt, Wenyi Wang, Jacob Bortman iD

Sensors · 30.06.2024 · 24 (13) · 4258

DOI: 10.3390/s24134258 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 30.06.2024. Verfasst von Omri Matania und 4 weiteren Autor:innen. Beteiligte Einrichtung: BGU-PHM Laboratory, Department of Mechanical Engineering, Ben-Gurion University of the Negev, P.O. Box 653, Beer Sheva 8410501, Israel. Hauptthemen laut MEDLINE: Algorithms, Signal Processing, Computer-Assisted. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Gear fault detection and remaining useful life estimation are important tasks for monitoring the health of rotating machinery. In this study, a new benchmark for endurance gear vibration signals is presented and made publicly available. The new dataset was used in the HUMS 2023 conference data challenge to test anomaly detection algorithms. A survey of the suggested techniques is provided, demonstrating that traditional signal processing techniques interestingly outperform deep learning algorithms in this case. Of the 11 participating groups, only those that used traditional approaches achieved good results on most of the channels. Additionally, we introduce a signal processing anomaly detection algorithm and meticulously compare it to a standard deep learning anomaly detection algorithm using data from the HUMS 2023 challenge and simulated signals. The signal processing algorithm surpasses the deep learning algorithm on all tested channels and also on simulated data where there is an abundance of training data. Finally, we present a new digital twin that enables the estimation of the remaining useful life of the tested gear from the HUMS 2023 challenge.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsSignal Processing, Computer-AssistedHumansVibrationDeep Learning

Stichwörter der Autor:innen

data-drivendeep learningdigital twingearvibration signals

Autor:innen und Institutionen

  • BGU-PHM Laboratory, Department of Mechanical Engineering, Ben-Gurion University of the Negev, P.O. Box 653, Beer Sheva 8410501, Israel.
  • GPMS International Inc., 93 Pilgram Place, Waterbury, VT 05676, USA.
  • Defence Science and Technology Group (DSTG), Department of Defence, Melbourne, VIC 3207, Australia.

ORCID-Profile: Omri Matania, Eric Bechhoefer, Jacob Bortman

Zitieren

APA

Matania, O., Bechhoefer, E., Blunt, D., Wang, W., & Bortman, J. (2024). Anomaly Detection and Remaining Useful Life Estimation for the Health and Usage Monitoring Systems 2023 Data Challenge. Sensors, 24(13), 4258. https://doi.org/10.3390/s24134258

Vancouver

Matania O, Bechhoefer E, Blunt D, Wang W, Bortman J. Anomaly Detection and Remaining Useful Life Estimation for the Health and Usage Monitoring Systems 2023 Data Challenge. Sensors. 2024;24(13):4258. doi:10.3390/s24134258

BibTeX
@article{Matania2024,
  author = {Matania, Omri and Bechhoefer, Eric and Blunt, David and Wang, Wenyi and Bortman, Jacob},
  title = {Anomaly Detection and Remaining Useful Life Estimation for the Health and Usage Monitoring Systems 2023 Data Challenge},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {13},
  pages = {4258},
  doi = {10.3390/s24134258}
}
Kostenlos starten →