Early fault detection in gearboxes via dynamic principal component analysis–driven multivariate statistical process control
PLOS One · 18.05.2026 · 21 (5) · e0348497
DOI: 10.1371/journal.pone.0348497 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift PLOS One, online erschienen am 18.05.2026. Verfasst von Antonio Pérez-Torres und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Applied Statistics and Operational Research, and Quality, Universitat Politècnica de València, València, Spain. Hauptthemen laut MEDLINE: Equipment Failure Analysis, Industry, Models, Statistical. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidad Politécnica Salesiana.
Abstract (Originalsprache)
Early detection of gearbox failure is essential due to their critical role in industrial operations. Therefore, effective condition monitoring techniques are required to identify incipient deviations in operational behaviour. Therefore, this study proposes a dynamic principal component analysis methodology, integrated within a multivariate statistical process control framework, to detect progressive failures in spur gearboxes from vibration signals. The signal is segmented into sub-windows and characterised using condition indicators in the time and frequency domains. Diagnosis is based on Hotelling’s T 2 statistic and the squared prediction error, which define statistical control limits to discriminate between normal and failure conditions. Empirical validation uses an experimental dataset covering combinations of load, speed, and failure severity. The results demonstrate high sensitivity to progressive degradation and accurate early-stage detection, supporting the multivariate statistical process control approach with dynamic principal component analysis as an effective tool for diagnosis and predictive maintenance in high-criticality industrial environments.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Applied Statistics and Operational Research, and Quality, Universitat Politècnica de València, València, Spain.
- Grupo de Investigación y Desarrollo en Tecnologías Industriales (GIDTEC), Universidad Politécnica Salesiana, Cuenca, Ecuador.
- Departamento de Estadística, Universidad de Concepción, Concepción, Chile.
- Facultad de Ingeniería y Arquitectura, Universidad Central de Chile, La Serena, Chile.
ORCID-Profile: Antonio Pérez-Torres, Jean Navarrete-Campos, Reinier Fernández-López, Susana Barceló-Cerdá
Förderung
- Universidad Politécnica Salesiana
Zitieren
APA
Pérez-Torres, A., Navarrete-Campos, J., Fernández-López, R., Figueroa-Zúñiga, J., & Barceló-Cerdá, S. (2026). Early fault detection in gearboxes via dynamic principal component analysis–driven multivariate statistical process control. PLOS One, 21(5), e0348497. https://doi.org/10.1371/journal.pone.0348497
Vancouver
Pérez-Torres A, Navarrete-Campos J, Fernández-López R, Figueroa-Zúñiga J, Barceló-Cerdá S. Early fault detection in gearboxes via dynamic principal component analysis–driven multivariate statistical process control. PLOS One. 2026;21(5):e0348497. doi:10.1371/journal.pone.0348497
BibTeX
@article{PrezTorres2026,
author = {Pérez-Torres, Antonio and Navarrete-Campos, Jean and Fernández-López, Reinier and Figueroa-Zúñiga, Jorge and Barceló-Cerdá, Susana},
title = {Early fault detection in gearboxes via dynamic principal component analysis–driven multivariate statistical process control},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {5},
pages = {e0348497},
doi = {10.1371/journal.pone.0348497}
}
EUVIMED