EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Methodology for Feature Selection of Time Domain Vibration Signals for Assessing the Failure Severity Levels in Gearboxes

Antonio Pérez-Torres, René-Vinicio Sánchez, Susana Barceló-Cerdá

Applied Sciences · 22.05.2025 · 15 (11) · 5813

DOI: 10.3390/app15115813 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 22.05.2025. Verfasst von Antonio Pérez-Torres und 2 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidad Politécnica Salesiana and Universitat Politècnica de València.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Early failure detection in gear systems reduces unplanned downtime and associated maintenance costs in rotating machinery. Although numerous indicators can be extracted from vibration signals, selecting the most relevant ones remains challenging. This study proposes a methodology for selecting time-domain features to classify fault severity levels in spur gearboxes. Vibration signals are acquired using six accelerometers and processed to extract 64 statistical condition indicators (CIs). The most informative subset of CIs is identified and selected through a wrapper-based selection approach and artificial intelligence tools. The selected features are then evaluated based on the classification accuracy and the area under the curve (AUC) in receiver operating characteristic (ROC) achieved using Random Forest (RF) and K-nearest neighbours (K-NN) models, with performance exceeding 98%. Additionally, the effect of sensor position and inclination on signal quality and classification performance is analysed using factorial analysis of variance (ANOVA) and multiple comparison tests. The results confirm the robustness of the selected CIs and the minimal influence of sensor placement variability, supporting the practical applicability of the proposed approach in industrial settings. The methodology offers a structured framework for selecting condition indicators in vibration signals, experimentally validated using multiple sensors and fault severity levels, and it is both automated and straightforward to implement.

Förderung

  • Universidad Politécnica Salesiana and Universitat Politècnica de València

Zitieren

APA

Pérez-Torres, A., Sánchez, R., & Barceló-Cerdá, S. (2025). Methodology for Feature Selection of Time Domain Vibration Signals for Assessing the Failure Severity Levels in Gearboxes. Applied Sciences, 15(11), 5813. https://doi.org/10.3390/app15115813

Vancouver

Pérez-Torres A, Sánchez R, Barceló-Cerdá S. Methodology for Feature Selection of Time Domain Vibration Signals for Assessing the Failure Severity Levels in Gearboxes. Applied Sciences. 2025;15(11):5813. doi:10.3390/app15115813

BibTeX
@article{PrezTorres2025,
  author = {Pérez-Torres, Antonio and Sánchez, René-Vinicio and Barceló-Cerdá, Susana},
  title = {Methodology for Feature Selection of Time Domain Vibration Signals for Assessing the Failure Severity Levels in Gearboxes},
  journal = {Applied Sciences},
  year = {2025},
  volume = {15},
  number = {11},
  pages = {5813},
  doi = {10.3390/app15115813}
}
Kostenlos starten →