.png){kind=icon}
.png){kind=icon}
Return
Conditioned Diffusion Framework for Temperature Field Generation via Multi-Source Physical Parameters Fusion and Sensor Layout-Decoupled Modeling
.png){kind=icon}
PRE
AI
Y
M
Q
M
Y
DOI：10.1016/j.ijheatmasstransfer.2026.129375.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• PRISM-Diffusion fuses multi-source physical parameters and measurements. • Physical parameters modulate noise prediction for reverse denoising. • A tailored training strategy adapts to diverse physical parameters. • Stochastic prior alignment decouples sensor configurations from model and training. • Unified probabilistic framework supports multiple zero-shot generation paradigms.
Journal
IF:
5.8
Papers:
2.5W
Citations:
10.2W
Organization
No organization information available
Cited Papers