.png){kind=icon}
.png){kind=icon}
Return
CIL-FGGM: A class-incremental learning framework based on fine-grained Gaussian mixture modeling for open-set fault recognition in rotating machinery
.png){kind=icon}
PRE
AI
B
H
W
J
T
DOI：10.1016/j.aei.2026.104779.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Open-set fault recognition framework developed for complex rotating machinery systems. • An IWKN-based model for multi-source sensor signal feature extraction is constructed. • A FGGM model is introduced to characterize complex fault feature distributions. • A CIL-FGGM framework is built to achieve open-set fault recognition in rotating machinery. • Different results demonstrate the excellent effectiveness of CIL-FGGM approach.
Keywords:
Open-set fault recognition
Class-incremental learning
Fine-grained Gaussian mixture modeling
Rotating machinery
Multi-source sensor signals
Journal
IF:
9.9
Papers:
4.0K
Citations:
1.7W
Organization
No organization information available
Cited Papers