EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Failure Profile Characterization in Heavy-Duty Trucks Using Fuzzy Clustering of Telemetry and Repair Data

Juliana Viscenheski, Ricardo Lüders, Heitor S Lopes, Thiago H Silva

Journal of Internet Services and Applications · 02.07.2026 · 17 (1) · 283-294

DOI: 10.5753/jisa.2026.7108 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Internet Services and Applications, online erschienen am 02.07.2026. Verfasst von Juliana Viscenheski und 3 weiteren Autor:innen. Die Arbeit nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Among transportation companies, the most expensive operational costs are due to the maintenance of truck fleets. Data-driven approaches that leverage telemetry and repair data can be effective in addressing such problems. Telemetry data is collected from sensors that monitor truck operational conditions, while repair data is recorded during both scheduled and emergency maintenance. This work characterizes the profiles of Euro 6 heavy-duty trucks using fuzzy clustering to identify vehicles with component failure, specifically within the powertrain system (engine/transmission assembly). Feature selection is based on correlation analysis and extracted from the time series of sensors. Three methods are used to characterize failure profiles: (i) a baseline strategy using averaged feature vectors of failed and non-failed trucks; (ii) Fuzzy C-Means (FCM); and (iii) Fuzzy Self-Organizing Maps (FSOM). These profiles are then used to compute failure risk scores for each truck, based on the similarity to failed and healthy truck references. Our contribution includes a detailed evaluation of FCM and FSOM parameters and their impact on failure results, as well as the identification of usage-related features as stronger predictors of failure than component-specific variables. Results show that the clustering-based strategy can significantly improve failure identification when compared to the baseline. This finding demonstrates the potential to support targeted preventive maintenance with reduced false positives.

Zitieren

APA

Viscenheski, J., Lüders, R., Lopes, H. S., & Silva, T. H. (2026). Failure Profile Characterization in Heavy-Duty Trucks Using Fuzzy Clustering of Telemetry and Repair Data. Journal of Internet Services and Applications, 17(1), 283-294. https://doi.org/10.5753/jisa.2026.7108

Vancouver

Viscenheski J, Lüders R, Lopes HS, Silva TH. Failure Profile Characterization in Heavy-Duty Trucks Using Fuzzy Clustering of Telemetry and Repair Data. Journal of Internet Services and Applications. 2026;17(1):283-294. doi:10.5753/jisa.2026.7108

BibTeX
@article{Viscenheski2026,
  author = {Viscenheski, Juliana and Lüders, Ricardo and Lopes, Heitor S and Silva, Thiago H},
  title = {Failure Profile Characterization in Heavy-Duty Trucks Using Fuzzy Clustering of Telemetry and Repair Data},
  journal = {Journal of Internet Services and Applications},
  year = {2026},
  volume = {17},
  number = {1},
  pages = {283--294},
  doi = {10.5753/jisa.2026.7108}
}
Kostenlos starten →