.png){kind=icon}
Return
Aerodynamic shape optimization via active learning-driven design space refinement
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ast.2025.110606.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A design space refinement mechanism is developed to efficiently identify compact, high-performance regions within the search space. • VAAL and LLAL are applied to promote effective and data-efficient exploration of the search space. • An optimization-tailored active learning framework is proposed to enhance surrogate model accuracy in critical regions with minimal labeling effort. • Experimental results demonstrate that the proposed approach outperforms conventional dimensionality reduction techniques in both optimization effectiveness and computational efficiency.
Journal
IF:
5.8
Papers:
1.0W
Citations:
3.0W
Organization
No organization information available
Cited Papers
ShareSaveAerodynamic shape optimization of a single turbine stage based on parameterized Free-Form Deformation with mapping design parameters.png)
ENERGY
ENERGYIF9.4
PREAI
ShareSaveShareSaveShareSaveShareSaveShareSaveShareSave
View more