Parametric shape optimization with differentiable FEM simulation
In this example, you will learn how to:
Build a Tesseract that wraps a differentiable finite-element solver from jax-fem.
Build a Tesseract that uses finite differences under the hood to enable differentiability of a non-autodifferentiable geometry operation (computing a signed distance field from a 3D model).
Compose both Tesseracts with Tesseract-JAX to create a pipeline that can be used for differentiable shape optimization.
Perform gradient-based optimization using optax on the Tesseract-JAX...
Read more at docs.pasteurlabs.ai