Abstract:Data streams in real-world industrial scenarios often contain transitional operating conditions that are uncovered during offline training, leading to significant distribution shifts. To bridge the gap between static offline models and dynamic online data, a novel asymmetric adaptation-based fault diagnosis method is proposed in this paper. Specifically, in the offline stage, we employ domain generalization techniques to extract domain-invariant features from multiple stable conditions and construct robust normalized fault prototypes as reference anchors. Subsequently, during online inference, we design an online test-time adaptation method based on a periodic prototype re-projection mechanism to dynamically update prototype positions. Furthermore, we utilize the geometric distribution derived from anchors to guide the updates of classifiers and adopt an asymmetric learning rate strategy for the feature extractor and classifier. The proposed approach ensures rapid adaptation to new transitional conditions while preserving the discriminative power inherited from the offline domain generalization initialization. Experimental results demonstrate that this mechanism effectively leverages offline generalized knowledge to guide online inference, significantly improving robustness in non-stationary environments.
| Comments: | 6 pages, 3 figures, Accepted by ICAIS & ISAS 2026 |
| Subjects: | Systems and Control (eess.SY); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.24457 [eess.SY] |
| (or arXiv:2605.24457v1 [eess.SY] for this version) | |
| https://doi.org/10.48550/arXiv.2605.24457 arXiv-issued DOI via DataCite (pending registration) |
From: Zeyi Liu [view email]
[v1]
Sat, 23 May 2026 08:10:16 UTC (2,354 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。