Surrogate-Based Differentiable Pipeline for Shape Optimization
By: Andrin Rehmann , Nolan Black , Josiah Bjorgaard and more
Potential Business Impact:
Lets computers design better things faster.
Gradient-based optimization of engineering designs is limited by non-differentiable components in the typical computer-aided engineering (CAE) workflow, which calculates performance metrics from design parameters. While gradient-based methods could provide noticeable speed-ups in high-dimensional design spaces, codes for meshing, physical simulations, and other common components are not differentiable even if the math or physics underneath them is. We propose replacing non-differentiable pipeline components with surrogate models which are inherently differentiable. Using a toy example of aerodynamic shape optimization, we demonstrate an end-to-end differentiable pipeline where a 3D U-Net full-field surrogate replaces both meshing and simulation steps by training it on the mapping between the signed distance field (SDF) of the shape and the fields of interest. This approach enables gradient-based shape optimization without the need for differentiable solvers, which can be useful in situations where adjoint methods are unavailable and/or hard to implement.
Similar Papers
Dflow-SUR: Enhancing Generative Aerodynamic Inverse Design using Differentiation Throughout Flow Matching
Computational Engineering, Finance, and Science
Designs better airplane wings faster.
Accelerating shape optimization by deep neural networks with on-the-fly determined architecture
Computational Engineering, Finance, and Science
Makes designs faster by learning from tests.
Accelerating shape optimization by deep neural networks with on-the-fly determined architecture
Computational Engineering, Finance, and Science
Makes designs faster by using smart computer guesses.