Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Surrogate-Based Differentiable Pipeline for Shape Optimization

About

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.

Andrin Rehmann, Nolan Black, Josiah Bjorgaard, Alessandro Angioi, Andrei Paleyes, Niklas Heim, Dion H\"afner, Alexander Lavin• 2025

Related benchmarks

TaskDatasetResultRank
Shape Optimization and InversionHelmholtz
Inference Time (ms)18.55
8
Forward prediction2D Helmholtz
Relative L1 Error18.84
8
Forward predictionAirFoil 9k
Relative L1 Error0.015
7
Shape Optimization and InversionAirfoil
Latency (ms)15.52
7
Airfoil Shape OptimizationAirFoil 9k
Lift Coefficient (CL)1.2
4
Showing 5 of 5 rows

Other info

Follow for update