Failure Detection in Sensors via Variational Autoencoders and Image-Based Feature Representation
Sensors · 29.03.2025 · 25 (7) · 2175
DOI: 10.3390/s25072175 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 29.03.2025. Verfasst von Luis Miguel Moreno Haro und 3 weiteren Autor:innen. Beteiligte Einrichtung: Laboratoire en Intelligence des Données, Department of Mathematical and Industrial Engineering, Polytechnique Montréal, Montréal, QC H3T 0A3, Canada. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Mitacs.
Abstract (Originalsprache)
This paper presents a novel approach for detecting sensor failures using image-based feature representation and the Convolutional Variational Autoencoder (CVAE) model. Existing methods are limited when analyzing multiple failure modes simultaneously or adapting to diverse sensor data. This limitation may compromise decision-making and system performance, hence the need for more flexible and resilient models. The proposed approach transforms sensor data into image-based feature representations of statistics such as mean, variance, kurtosis, entropy, skewness, and correlation. The CVAE is trained on such image representations, and the corresponding reconstruction error leads to a Health Index (HI) for detecting multiple sensor failures. Moreover, the CVAE latent space is used to define a complementary HI and a convenient visualization tool, enhancing the interpretability of the proposed approach. The evaluation of the proposed detection approach with data comprising diverse configurations of faulty sensors showed encouraging results. The proposed approach is illustrated in an industrial case study emerging from the aeronautical domain, with data from a complex electromechanical system comprising nearly 80 sensor measurements at a 1 Hz sampling rate. The results demonstrate the potential of the proposed method in detecting multiple sensor failures.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Laboratoire en Intelligence des Données, Department of Mathematical and Industrial Engineering, Polytechnique Montréal, Montréal, QC H3T 0A3, Canada.
- Department of Mechanical Engineering, École de Technologie Supérieure, Montréal, QC H3C 1K3, Canada.
ORCID-Profile: Bruno Agard, Antoine Tahan
Förderung
- Mitacs
Zitieren
APA
Moreno Haro, L. M., Oliveira-Filho, A., Agard, B., & Tahan, A. (2025). Failure Detection in Sensors via Variational Autoencoders and Image-Based Feature Representation. Sensors, 25(7), 2175. https://doi.org/10.3390/s25072175
Vancouver
Moreno Haro LM, Oliveira-Filho A, Agard B, Tahan A. Failure Detection in Sensors via Variational Autoencoders and Image-Based Feature Representation. Sensors. 2025;25(7):2175. doi:10.3390/s25072175
BibTeX
@article{MorenoHaro2025,
author = {Moreno Haro, Luis Miguel and Oliveira-Filho, Adaiton and Agard, Bruno and Tahan, Antoine},
title = {Failure Detection in Sensors via Variational Autoencoders and Image-Based Feature Representation},
journal = {Sensors},
year = {2025},
volume = {25},
number = {7},
pages = {2175},
doi = {10.3390/s25072175}
}
EUVIMED