An Unsupervised Learning Approach for Wayside Train Wheel Flat Detection
Sensors · 08.02.2023 · 23 (4) · 1910
DOI: 10.3390/s23041910 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 08.02.2023. Verfasst von Mohammadreza Mohammadi und 5 weiteren Autor:innen. Beteiligte Einrichtung: CONSTRUCT-LESE, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: This work was financially supported by Base Funding-UIDB/04708/2020 and Programmatic Funding-UIDP/04708/2020 of the CONSTRUCT - Instituto de Estruturas e Constr…, The paper reflects research developed in the ambit of the project Way4SafeRail, NORTE-01-0247-FEDER-069595, founded by Agência Nacional de Inovação S.A., progr…, The second author acknowledges Grant no. 2021.04272.CEECIND from the Stimulus of Scientific Employment, Individual Support (CEECIND) - 4rd Edition provided by….
Abstract (Originalsprache)
One of the most common types of wheel damage is flats which can cause high maintenance costs and enhance the probability of failure and damage to the track components. This study aims to compare the performance of four feature extraction methods, namely, auto-regressive (AR), auto-regressive exogenous (ARX), principal component analysis (PCA), and continuous wavelet transform (CWT) capable of automatically distinguishing a defective wheel from a healthy one. The rail acceleration for the passage of freight vehicles is used as a reference measurement to perform this study which comprises four steps: (i) feature extraction from acquired responses using the specific feature extraction methods; (ii) feature normalization based on a latent variable method; (iii) data fusion to enhance the sensitivity to recognize defective wheels; and (iv) damage detection by performing an outlier analysis. The results of this research show that AR and ARX extraction methods are more efficient techniques than CWT and PCA for wheel flat damage detection. Furthermore, in almost every feature, a single sensor on the rail is sufficient to identify a defective wheel. Additionally, AR and ARX methods demonstrated the potential to distinguish a defective wheel on the left and right sides. Lastly, the ARX method demonstrated robustness to detect the wheel flat with accelerometers placed only in the sleepers.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- CONSTRUCT-LESE, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal.
- CONSTRUCT, School of Engineering, Polytechnic of Porto, 4249-015 Porto, Portugal.
ORCID-Profile: Araliya Mosleh, Cecilia Vale, Diogo Ribeiro, Pedro Montenegro, Andreia Meixedo
Förderung
- This work was financially supported by Base Funding-UIDB/04708/2020 and Programmatic Funding-UIDP/04708/2020 of the CONSTRUCT - Instituto de Estruturas e Constr…
- The paper reflects research developed in the ambit of the project Way4SafeRail, NORTE-01-0247-FEDER-069595, founded by Agência Nacional de Inovação S.A., progr…
- The second author acknowledges Grant no. 2021.04272.CEECIND from the Stimulus of Scientific Employment, Individual Support (CEECIND) - 4rd Edition provided by…
- CONSTRUCT—Instituto de Estruturas e Construções
- national funds
- FCT—Fundação para a Ciência e Tecnologia
Zitieren
APA
Mohammadi, M., Mosleh, A., Vale, C., Ribeiro, D., Montenegro, P., & Meixedo, A. (2023). An Unsupervised Learning Approach for Wayside Train Wheel Flat Detection. Sensors, 23(4), 1910. https://doi.org/10.3390/s23041910
Vancouver
Mohammadi M, Mosleh A, Vale C, Ribeiro D, Montenegro P, Meixedo A. An Unsupervised Learning Approach for Wayside Train Wheel Flat Detection. Sensors. 2023;23(4):1910. doi:10.3390/s23041910
BibTeX
@article{Mohammadi2023,
author = {Mohammadi, Mohammadreza and Mosleh, Araliya and Vale, Cecilia and Ribeiro, Diogo and Montenegro, Pedro and Meixedo, Andreia},
title = {An Unsupervised Learning Approach for Wayside Train Wheel Flat Detection},
journal = {Sensors},
year = {2023},
volume = {23},
number = {4},
pages = {1910},
doi = {10.3390/s23041910}
}
EUVIMED