A Generalized Convolutional Neural Network Model Trained on Simulated Data for Fault Diagnosis in a Wide Range of Bearing Designs
Sensors · 09.04.2025 · 25 (8) · 2378
DOI: 10.3390/s25082378 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 09.04.2025. Verfasst von Amirmasoud Kiakojouri und 1 weiteren Autor:innen. Beteiligte Einrichtung: National Centre for Advanced Tribology at Southampton (nCATS), School of Engineering, University of Southampton, Southampton SO17 1BJ, UK. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Schaeffler Technologies, University of Southampton, and the framework of Clean Sky 2 Joint Undertaking through the 82 European Union Horizon 2020 Research and….
Abstract (Originalsprache)
Rolling element bearings (REBs) are critical components in rotating machinery and a leading cause of machine failures. Traditional fault detection methods rely on signal processing, but advances in machine learning (ML) and deep learning (DL) have dramatically improved diagnostic accuracy. However, existing DL models struggle with data availability, generalization, and domain adaptation, making industrial applications challenging. This study proposes a convolutional neural network (CNN) model trained on numerically simulated vibration data generated for a wide range of bearing designs. A novel hybrid signal processing method is employed to enhance feature extraction and reduce domain shifts between simulated and real-world data. The optimized CNN model, trained on simulated data, is tested using experimental and real-world vibration signals from laboratory bearings and jet engine components. The results show high classification accuracy using data from the Case Western Reserve University experimental dataset and successful fault detection in real-world Safran jet engine ground tests. The findings demonstrate the effectiveness of the developed CNN-based model for bearing fault classification, tackling training data scarcity and generalizability challenges while contributing to the development of intelligent fault diagnosis models for several industrial applications.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- National Centre for Advanced Tribology at Southampton (nCATS), School of Engineering, University of Southampton, Southampton SO17 1BJ, UK.
ORCID-Profile: Amirmasoud Kiakojouri, Ling Wang
Förderung
- Schaeffler Technologies, University of Southampton, and the framework of Clean Sky 2 Joint Undertaking through the 82 European Union Horizon 2020 Research and…
Zitieren
APA
Kiakojouri, A., & Wang, L. (2025). A Generalized Convolutional Neural Network Model Trained on Simulated Data for Fault Diagnosis in a Wide Range of Bearing Designs. Sensors, 25(8), 2378. https://doi.org/10.3390/s25082378
Vancouver
Kiakojouri A, Wang L. A Generalized Convolutional Neural Network Model Trained on Simulated Data for Fault Diagnosis in a Wide Range of Bearing Designs. Sensors. 2025;25(8):2378. doi:10.3390/s25082378
BibTeX
@article{Kiakojouri2025,
author = {Kiakojouri, Amirmasoud and Wang, Ling},
title = {A Generalized Convolutional Neural Network Model Trained on Simulated Data for Fault Diagnosis in a Wide Range of Bearing Designs},
journal = {Sensors},
year = {2025},
volume = {25},
number = {8},
pages = {2378},
doi = {10.3390/s25082378}
}
EUVIMED