Szczegóły publikacji
Opis bibliograficzny
Reducing negative transfer in domain adaptation for vibration fault diagnosis / Paweł KNAP, Urszula JACHYMCZYK // W: PHME 2026 [Dokument elektroniczny] : proceedings of the 9th European conference of the Prognostics and Health Management Society 2026 : Oslo, Norway, July 8th-10th 2026 / ed. by Phuc Do, Cordelia Ezhilarasu, Anibal Bregon. — Wersja do Windows. — Dane tekstowe. — [USA] : PHM Society, [2026]. — e-ISBN: 978-1-936263-44-8. — S. 1-12. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 11-12, Abstr. — Publikacja dostępna online od: 2026-07-03
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 170308 |
|---|---|
| Data dodania do BaDAP | 2026-10-30 |
| Tekst źródłowy | URL |
| DOI | 10.36001/phme.2026.v9i1.4926 |
| Rok publikacji | 2026 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Creative Commons | |
Abstract
Unsupervised domain adaptation (UDA) for vibration-based fault diagnosis can improve transfer across changing operating conditions, but its reliability remains a practical concern. In particular, large domain shifts can lead to negative transfer, where an adapted model underperforms a source-only baseline. This motivates evaluation beyond average gains, with emphasis on worst-case behavior and failure modes relevant to deployment. This study proposes a lightweight safeguard for discrepancy-based UDA that does not require labeled target data. The approach augments standard adaptation with an unlabeled monitoring rule based on target prediction entropy and alignment-loss trends. When adaptation appears unstable, training is paused and the model is rolled back to a safer checkpoint. The safeguard is designed as a small reliability layer on top of existing UDA pipelines rather than as a new adaptation method. We evaluate source-only training, standard UDA, source-pretrained UDA, and safeguarded UDA on the Case Western Reserve University (CWRU) and Paderborn University (PU) bearing datasets under multiple cross-condition transfer tasks. Experiments include raw time-domain, FFT-based, and STFT-based representations with MMD- and CORAL-based adaptation. Results show that negative transfer is a repeatable phenomenon, particularly on more challenging CWRU shifts, while source-pretrained UDA substantially affects reliability. The safeguard shows partial mitigation of harmful adaptation in selected PU cases but does not consistently prevent degradation across all scenarios. Overall, the results highlight that monitoring adaptation dynamics can improve reliability in some settings, but that safe deployment of UDA for fault diagnosis still requires explicit consideration of worst-case behavior and baseline comparisons.
