Szczegóły publikacji
Opis bibliograficzny
Advanced domain adaptation for fault diagnosis in condition monitoring / Paweł KNAP, Ireneusz DOMINIK // W: MMAR 2025 [Dokument elektroniczny] : 29th international conference on Methods and Models in Automation and Robotics : 26–29 August 2025, Międzyzdroje, Poland : technical papers : on line proceedings. — Wersja do Windows. — Dane tekstowe. — Piscataway : IEEE, cop. 2025. — ( International Conference on Methods and Models in Automation and Robotics ; ISSN 2835-2815 ). — USB ISBN: 979-8-3315-2648-1. — Print on Demand(PoD) ISBN: 979-8-3315-2650-4. — e-ISBN: 979-8-3315-2649-8. — S. 53–58. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 57–58, Abstr.
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 162268 |
|---|---|
| Data dodania do BaDAP | 2025-09-12 |
| Tekst źródłowy | URL |
| DOI | 10.1109/MMAR65820.2025.11150893 |
| Rok publikacji | 2025 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Institute of Electrical and Electronics Engineers (IEEE) |
| Konferencja | International Conference on Methods and Models in Automation and Robotics 2025 |
| Czasopismo/seria | International Conference on Methods and Models in Automation and Robotics |
Abstract
This paper presents an advanced approach to fault diagnosis and condition monitoring by integrating domain adaptation techniques into a Bayesian-optimized feature extraction framework. Specifically, we enhance model generalization by incorporating Maximum Mean Discrepancy (MMD) and CORrelation ALignment (CORAL) loss functions, which align feature distributions between source and target domains. Experiments conducted on the widely used Case Western Reserve University (CWRU) bearing dataset demonstrate that the proposed methods outperform a baseline model trained solely on source data, achieving higher accuracy and robustness under varying operational conditions. These results underscore the potential of advanced domain adaptation strategies for reliable predictive maintenance applications.
