A domain feature decoupling network for rotating machinery fault diagnosis under unseen operating conditions
Lists
Only you see this
Abstract
Highlights•A fault diagnosis model with strong domain generalization performance is developed to accurately determine the health status of rotating machinery under unseen operating conditions.•A creative feature decoupling method is adopted to achieve efficient knowledge mining of domain-invariant features.•A self-learning joint optimization strategy is proposed to drive the parameter optimization of DFDN.
BibTeX
@inproceedings{gao2024domain,
author = {Tianyu Gao and Jingli Yang and Wenmin Wang and Xiaopeng Fan},
title = {{A domain feature decoupling network for rotating machinery fault diagnosis under unseen operating conditions}},
booktitle = {Reliab. Eng. Syst. Saf},
year = {2024},
url = {https://openreview.net/forum?id=IZIjToEcHP},
}Loading related content...