Metraipolis › archive › dc_a72c844c35c2

Mixture of Polyconvex Neural Potentials for Parametric Hyperelasticity: Towards Foundation Material Models — arXiv:2609.00359

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00359
License (as archived)
CC0-1.0
Archived
2026-10-17T07:21:27.976Z
SHA-256 of the archived text
caf14d96b443abc519e557e54cf69f8a9d41d55cb00fae29dc818852af6dec1a
Stable URL of this page
https://metraipolis.com/documento/dc_a72c844c35c2

How to cite

Mixture of Polyconvex Neural Potentials for Parametric Hyperelasticity: Towards Foundation Material Models — arXiv:2609.00359 — arXiv (en), https://arxiv.org/abs/2609.00359 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a72c844c35c2 (Metraipolis archive dc_a72c844c35c2, sha256 caf14d96b443abc519e557e54cf69f8a9d41d55cb00fae29dc818852af6dec1a)
BibTeX
@misc{dca72c844c35c2,
  title = {Mixture of Polyconvex Neural Potentials for Parametric Hyperelasticity: Towards Foundation Material Models — arXiv:2609.00359},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00359},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a72c844c35c2; sha256 caf14d96b443abc519e557e54cf69f8a9d41d55cb00fae29dc818852af6dec1a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00359. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Hyperelastic constitutive models enable modeling large deformations in elastic solids. In common practice, a strain energy density function is prescribed in advance and model-specific parameters are calibrated from experiments. However, many applications require constitutive models for a family of related materials whose mechanical behavior varies with composition. A fixed constitutive model-form may not capture the full range of behavior across the family, while fitting separate forms does not provide a direct way to predict the response of new compositions. Recent work has developed data-driven constitutive models that learn flexible strain energy functions while incorporating key physical constraints. In this work, we propose using mixtures of convex neural potentials based on input convex neural networks as a modular and data efficient approach to modeling material families. Each potential is convex and monotonic with respect to polyconvex strain invariants, while a conditioning network maps material descriptors to mixture weights. We compare the approach with a monolithic partially input-convex neural network using experimental data from PolyJet 3D-printed materials and a synthetic Gent-type benchmark. Across both benchmarks, the mixture architecture generalized better to material descriptors not seen during training. In the PolyJet experimental benchmark, we showed that the mixture architecture is less sensitive to model hyperparameters, while in the Gent-type benchmark it generalized more reliably with sparse data in the material-descriptor space. These results suggest that representing a material family through a small set of shared convex neural potentials provides a useful structural prior for learning descriptor-dependent constitutive behavior from limited data.

Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-09-02 in physics.comp-ph).
Categorie arXiv: Computational Physics (physics.comp-ph) ; Materials Science (cond-mat.mtrl-sci).
Pagina del lavoro: https://arxiv.org/abs/2609.00359 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T07:16:49.912Z dalla pagina https://arxiv.org/catchup/physics.comp-ph/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).