Hua, Zehui, Sehri, Mert et Dumond, Patrick.
2025.
« Bearing fault diagnosis using text analysis on the CWRU dataset ».
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
327 - Bearing fault diagnosis using text.pdf - Version publiée Licence d'utilisation : Tous les droits réservés aux détenteurs du droit d'auteur. Télécharger (195kB) | Prévisualisation |
Résumé
Over the past decade, there has been increasing use of machine learning (ML) algorithms for fault detection by ML researchers. This emergence is due to the ever growing need for diagnosing bearing components to prevent catastrophic machine failures in industry. More recently, large language models (LLMs) have raised huge attention from both researchers and engineers. LLMs could be used in many applications like text classification and sentiment analysis. Compared with the commonly used inputs in intelligent fault diagnosis, fault diagnosis based on text analysis is very intuitive and easy to understand and thus shows great potential. This paper presents a preliminary analysis of bearing data by extracting features into a text file, followed by ML algorithm analysis to achieve accurate diagnostics.
| 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 15:12 |
| Dernière modification: | 18 déc. 2025 15:12 |
| URI: | https://espace2.etsmtl.ca/id/eprint/32421 |
Actions (Authentification requise)
 |
Dernière vérification avant le dépôt |