Fault Detection and Monitoring in Induction Machines Using Data-Driven Model Drift Detection
Sensors · 04.03.2026 · 26 (5) · 1595
DOI: 10.3390/s26051595 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 04.03.2026. Verfasst von Abdiel Ricaldi-Morales und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering, University of Chile, Av. Tupper 2007, Santiago 8370451, Chile. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agencia Nacional de Investigación y Desarrollo, National Agency for Research and Development (ANID) through the Scholarship Program “DOCTORADO BECAS CHILE 2023”, Advanced Center for Electrical and Electronic Engineering.
Abstract (Originalsprache)
Stator short-circuit faults (SSCFs) account for a significant portion of induction motor failures, yet their early detection remains a challenge in industrial environments where labeled fault data is scarce and installing additional sensors is often impractical. This paper proposes a novel, data-driven fault detection and diagnosis framework grounded in the Residual Information Value (RIV) principle to overcome reliability limitations of traditional spectral and residual energy methods. By redefining fault detection as a statistical test of independence between control inputs (voltages) and current residuals, the proposed method identifies incipient faults as model drifts without relying on prior knowledge of fault distributions. A key contribution of this work is the seamless integration of the diagnostic scheme into standard Variable Speed Drives (VSDs): the healthy nominal model (a Multilayer Perceptron) is trained exclusively using data from the drive’s existing self-commissioning routine, eliminating the need for manual data collection or complex physical parameter identification. Experimental validation on an industrial test bench demonstrates that the framework achieves superior diagnostic performance compared to traditional baselines, providing higher statistical separability and a reduced false alarm rate. The system can detect 1% incipient faults in approximately 61 ms while accurately identifying the faulty phase. The results confirm that the proposed RIV-based strategy offers a robust, non-intrusive, and industry-ready solution for predictive maintenance that effectively balances high-speed detection with enhanced statistical reliability.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electrical Engineering, University of Chile, Av. Tupper 2007, Santiago 8370451, Chile.
- Facultad de Ingeniería y Arquitectura, Universidad Central de Chile, Av. Santa Isabel 1186, Santiago 8330601, Chile.
ORCID-Profile: Abdiel Ricaldi-Morales, Camilo Ramírez, Jorge F Silva, Manuel A Duarte-Mermoud, Marcos E Orchard
Förderung
- Agencia Nacional de Investigación y Desarrollo
- National Agency for Research and Development (ANID) through the Scholarship Program “DOCTORADO BECAS CHILE 2023”
- Advanced Center for Electrical and Electronic Engineering
Zitieren
APA
Ricaldi-Morales, A., Ramírez, C., Silva, J. F., Duarte-Mermoud, M. A., & Orchard, M. E. (2026). Fault Detection and Monitoring in Induction Machines Using Data-Driven Model Drift Detection. Sensors, 26(5), 1595. https://doi.org/10.3390/s26051595
Vancouver
Ricaldi-Morales A, Ramírez C, Silva JF, Duarte-Mermoud MA, Orchard ME. Fault Detection and Monitoring in Induction Machines Using Data-Driven Model Drift Detection. Sensors. 2026;26(5):1595. doi:10.3390/s26051595
BibTeX
@article{RicaldiMorales2026,
author = {Ricaldi-Morales, Abdiel and Ramírez, Camilo and Silva, Jorge F and Duarte-Mermoud, Manuel A and Orchard, Marcos E},
title = {Fault Detection and Monitoring in Induction Machines Using Data-Driven Model Drift Detection},
journal = {Sensors},
year = {2026},
volume = {26},
number = {5},
pages = {1595},
doi = {10.3390/s26051595}
}
EUVIMED