.png){kind=icon}
.png){kind=icon}
Return
One-class-supervised fault diagnosis using flow-encoded subspace clustering
.png){kind=icon}
PRE
AI
C
L
Q
Z
杨
DOI：10.1016/j.asoc.2026.116191.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A flow-encoded subspace clustering (FESC) is proposed for one-class fault diagnosis. • FESC integrates a flow-based model and DCAE for distribution-aligned feature learning. • Pseudo-supervised subspace clustering enhances fault pattern discrimination ability. • FESC unifies semi-supervised anomaly detection and unsupervised clustering for intelligent health management.
Journal
IF:
6.6
Papers:
1.4W
Citations:
4.8W
Organization
Cited Papers