Mesh2Shell Neural Operator for Inverse Shape Optimization
Organizations: Computing and Mathematical Sciences, California Institute of Technology
Abstract
Physics-driven design seeks high-performing geometries, which need not conform to a learned shape category. Parametric and latent-space approaches facilitate surrogate-based optimization, but restrict deformations to prescribed shape families or learned decoders. We introduce the Mesh-to-Shell Neural Operator (M2S-NO) as the mesh-to-shell component of a category-agnostic inverse shape optimization framework. We separate the explicit mesh used for design from the volumetric representation used for physics prediction. M2S-NO maps oriented surface samples to a surface-centered shell representation, such as TruncatedSDF or HeatSDF. A separate problem-specific PDE neural operator (PDE-NO) maps this representation to physical fields. Objective gradients update mesh vertices through both operators, without a latent shape decoder. Preconditioning and remeshing support free-form deformation, while fixed interfaces are controlled directly on the mesh. Optional shell-space proposals enable topology changes. We evaluate geometric matching, jet-engine brackets, and neutron moderators, with independent FEM and OpenMC evaluation. Relative to the best training designs, M2S-NO reduces maximum bracket displacement by 14.3% and increases neutron-sensor current by 13.8%. Optimization also succeeds from an out-of-distribution bracket initialization, demonstrating the framework's geometric flexibility.
Figures & tables
| Starting point | Independent reference | Optimization results | ||
|---|---|---|---|---|
| Starting shape | Initial value | Dataset best | GANO | M2S-NO (ours) |
| In-distribution | 0.2446 | 0.1788 | 0.1884 | 0.1532 |
| Arch-augmented OOD | 0.1915 | 0.1788 | – | 0.1549 |
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Neural Operators
Neural operators learn mappings between functions, enabling fast surrogates for PDEs and other continuous physical systems.
See all 346 papers