EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Source Diagnosis of Bearing Faults Using Interpretable Boosted Trees

Miguel Fernández-Temprano iD, Manuel Astorgano-Antón iD, Óscar Duque-Pérez iD, Vanesa Fernandez-Cavero iD, Daniel Morinigo-Sotelo iD

Sensors · 03.03.2026 · 26 (5) · 1576

DOI: 10.3390/s26051576 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 03.03.2026. Verfasst von Miguel Fernández-Temprano und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics and Operational Research, Escuela de Ingenierías Industriales, Universidad de Valladolid, 47011 Valladolid, Spain. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The early detection and diagnosis of faults in induction motors is vital in today’s industry, since these are the motors used for the largest number of applications in the industrial environment and failure to detect a fault early can lead to significant losses. Bearing faults are the main problems detected in induction motors and several techniques have been developed to detect them. The use of the information contained in the motor vibrations is the main traditional source for its diagnosis, although there are also proposals that use the supply current, or the sound of the motor. Furthermore, these variables can be used in the time domain or in the frequency domain. The purpose of this work is to use explainable artificial intelligence (XAI) to determine which of these variables, and in which domain, contributes most to a correct diagnosis and how much can be gained in diagnosis by using multisensor data fusion. To carry out this comparison in the most objective way possible, a model selection procedure is proposed and boosting techniques are considered that prove to give a very precise diagnosis. The obtained diagnostic rules are then interpreted using SHAP values, a recent interpretation technique for complex classification procedures.

Schlagwörter

Stichwörter der Autor:innen

SHAP valuesboosted treesdata fusiondiagnostic expert systemsinduction motorsmonitoring

Autor:innen und Institutionen

  • Department of Statistics and Operational Research, Escuela de Ingenierías Industriales, Universidad de Valladolid, 47011 Valladolid, Spain.
  • Department of Electrical Engineering, Escuela de Ingenierías Industriales, Universidad de Valladolid, 47011 Valladolid, Spain.

ORCID-Profile: Miguel Fernández-Temprano, Manuel Astorgano-Antón, Óscar Duque-Pérez, Vanesa Fernandez-Cavero, Daniel Morinigo-Sotelo

Zitieren

APA

Fernández-Temprano, M., Astorgano-Antón, M., Duque-Pérez, Ó., Fernandez-Cavero, V., & Morinigo-Sotelo, D. (2026). Multi-Source Diagnosis of Bearing Faults Using Interpretable Boosted Trees. Sensors, 26(5), 1576. https://doi.org/10.3390/s26051576

Vancouver

Fernández-Temprano M, Astorgano-Antón M, Duque-Pérez Ó, Fernandez-Cavero V, Morinigo-Sotelo D. Multi-Source Diagnosis of Bearing Faults Using Interpretable Boosted Trees. Sensors. 2026;26(5):1576. doi:10.3390/s26051576

BibTeX
@article{FernndezTemprano2026,
  author = {Fernández-Temprano, Miguel and Astorgano-Antón, Manuel and Duque-Pérez, Óscar and Fernandez-Cavero, Vanesa and Morinigo-Sotelo, Daniel},
  title = {Multi-Source Diagnosis of Bearing Faults Using Interpretable Boosted Trees},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {5},
  pages = {1576},
  doi = {10.3390/s26051576}
}
Kostenlos starten →