Cakir, Efe et Dumond, Patrick.
2025.
« A comparative analysis of reinforcement learning and conventional deep learning approaches for bearing fault diagnosis ».
In Proceedings of the CSME-CFDSC-CSR 2025 International Congress (Montreal, QC, Canada, May 25-28, 2025)
Coll. « Progress in Canadian Mechanical Engineering », vol. 8.
Prévisualisation |
PDF
411 - A comparative analysis of reinforc.pdf - Version publiée Licence d'utilisation : Tous les droits réservés aux détenteurs du droit d'auteur. Télécharger (549kB) | Prévisualisation |
Résumé
Bearing faults in rotating machinery can lead to significant operational disruptions and maintenance costs. Modern methods for bearing fault diagnosis rely heavily on vibration analysis and machine learning techniques, which often require extensive labeled data and may not adapt well to dynamic environments. This study explores the feasibility of reinforcement learning (RL), specifically Deep Q-Networks (DQNs) for bearing fault classification tasks in machine condition monitoring to enhance the accuracy and adaptability of bearing fault diagnosis. The results demonstrate that RL models developed in this study can match the performance of traditional supervised learning models under controlled conditions, they excel in adaptability when equipped with optimized reward structures. However, their computational demands highlight areas for further improvement. These findings demonstrate RL’s potential to complement traditional methods, paving the way for adaptive diagnostic frameworks.
| Type de document: | Compte rendu de conférence |
|---|---|
| Éditeurs: | Éditeurs ORCID Hof, Lucas A. NON SPÉCIFIÉ Di Labbio, Giuseppe NON SPÉCIFIÉ Tahan, Antoine NON SPÉCIFIÉ Sanjosé, Marlène NON SPÉCIFIÉ Lalonde, Sébastien NON SPÉCIFIÉ Demarquette, Nicole R. NON SPÉCIFIÉ |
| Date de dépôt: | 18 déc. 2025 15:08 |
| Dernière modification: | 18 déc. 2025 15:08 |
| URI: | https://espace2.etsmtl.ca/id/eprint/32367 |
Actions (Authentification requise)
 |
Dernière vérification avant le dépôt |