Dflow-SUR: Enhancing Generative Aerodynamic Inverse Design using Differentiation Throughout Flow Matching
By: Aobo Yang , Zhen Wei , Rhea Liem and more
Potential Business Impact:
Designs better airplane wings faster.
Generative inverse design requires incorporating physical constraints to ensure that generated designs are both reliable and accurate. However, we observe that current state-of-the-art energy-based methods suffer from an asynchronous phenomenon, where the optimization of the physical loss is constrained by the flow matching inference process. To overcome this limitation, we introduce Dflow-SUR, a differentiation strategy that separates the optimization of the physical loss from the flow matching inference. Compared to the most advanced energy-based baseline, Dflow-SUR achieves a reduction in physical loss by four orders of magnitude, while also cutting wall-clock time by 74% on the airfoil case. Additionally, it increases the mean lift-to-drag ratio by 11.8% over traditional Latin-hypercube sampling in wing design. Beyond improvements in accuracy and efficiency, Dflow-SUR offers three additional practical advantages: (i) enhanced control over guidance, (ii) lower surrogate uncertainty, and (iii) greater robustness to hyper-parameter tuning. Together, these results demonstrate that Dflow-SUR is a highly promising framework, providing both scalability and high fidelity for generative aerodynamic design.
Similar Papers
Surrogate-Based Differentiable Pipeline for Shape Optimization
Computational Engineering, Finance, and Science
Lets computers design better things faster.
Going with the Speed of Sound: Pushing Neural Surrogates into Highly-turbulent Transonic Regimes
Computational Engineering, Finance, and Science
Helps design airplane wings faster and better.
Geometric and Physical Constraints Synergistically Enhance Neural PDE Surrogates
Machine Learning (CS)
Makes computer weather forecasts more accurate.