.png){kind=icon}
.png){kind=icon}
Return
Breaking the data scarcity barrier in HVAC fault diagnosis via feature-sample collaborative augmentation
.png){kind=icon}
OA
AI
J
C
K
Y
A
DOI：10.1016/j.apenergy.2026.128607.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• FSCA framework breaks data scarcity barrier in HVAC fault diagnosis. • Spatially correlated feature mapping converts 1D features into 2D images. • Improved diffusion model generates high-fidelity samples from limited data. • Diagnostic accuracy improves by up to 15.18% under extreme scarcity. • Proposed method outperforms SOTA GAN-based and oversampling baselines.
Keywords:
HVAC system
Fault detection and diagnosis
Diffusion model
Deep learning
Feature enhancement
Data augmentation
Journal
IF:
11
Papers:
2.6W
Citations:
17.8W
Organization
Cited Papers