Pre-training AeroTransformer on nearly 30,000 diverse wing geometries and fine-tuning with 450 specific samples achieves 0.36% error on surface-flow prediction for transonic wings, an 84.2% reduction versus training from scratch.
Deep learning methods for reynolds-averaged navier–stokes simulations of airfoil flows.AIAA Journal, 58(1):25–36, 2020
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
SuperWing supplies 4,239 diverse wing shapes and 28,856 flow-field solutions that let Transformer models predict surface aerodynamics to 2.5 drag-count error and generalize zero-shot to DLR-F6 and NASA CRM wings.
citing papers explorer
-
Towards a Foundation-Model Paradigm for Aerodynamic Prediction in Three-dimensional Design
Pre-training AeroTransformer on nearly 30,000 diverse wing geometries and fine-tuning with 450 specific samples achieves 0.36% error on surface-flow prediction for transonic wings, an 84.2% reduction versus training from scratch.
-
SuperWing: a comprehensive transonic wing dataset for data-driven aerodynamic design
SuperWing supplies 4,239 diverse wing shapes and 28,856 flow-field solutions that let Transformer models predict surface aerodynamics to 2.5 drag-count error and generalize zero-shot to DLR-F6 and NASA CRM wings.