Metraipolis › archive › dc_e9265fb784ba
A variational physics-informed graph neural network for heterogeneous solid mechanics — arXiv:2609.10983
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.10983
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T05:55:14.349Z
- SHA-256 of the archived text
79470ffd65310caae4088994f3a30312757517603b154d0ce7b2c4e8bb55485b- Stable URL of this page
https://metraipolis.com/documento/dc_e9265fb784ba
How to cite
A variational physics-informed graph neural network for heterogeneous solid mechanics — arXiv:2609.10983 — arXiv (en), https://arxiv.org/abs/2609.10983 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e9265fb784ba (Metraipolis archive dc_e9265fb784ba, sha256 79470ffd65310caae4088994f3a30312757517603b154d0ce7b2c4e8bb55485b)
BibTeX
@misc{dce9265fb784ba,
title = {A variational physics-informed graph neural network for heterogeneous solid mechanics — arXiv:2609.10983},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.10983},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e9265fb784ba; sha256 79470ffd65310caae4088994f3a30312757517603b154d0ce7b2c4e8bb55485b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10983. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Stress localization in heterogeneous solids is governed by the bimaterial interface, where the displacement field remains $C^0$-continuous, while in-plane stresses jump due to the stiffness mismatch. Coordinate-based physics-informed neural networks (PINNs) represent this jump via a prescribed regularization width or a weighted interface penalty, making their accuracy sensitive to how phase-contrast changes are handled. This work presents a variational, label-free physics-informed graph neural network (PI-GNN) in which the heterogeneity is carried by the discretization rather than by the trial field. The solver operates on a conforming adaptive mesh graph, assigns constitutive behavior per element, and minimizes the discrete total potential energy as a single unweighted objective in which only first derivatives appear. The discrete energy on piecewise-linear elements coincides with the finite element (FE) Ritz functional. Dirichlet conditions are enforced by construction, with no penalty term, no interface weight, and no prescribed transition width. Using one fixed architecture, optimizer, and loss across small-strain elasticity and finite-strain Neo-Hookean hyperelasticity in two and three dimensions, the von Mises error remains below $3.58\%$ across a stiffness-contrast sweep spanning $(E_{\mathrm{inc}}/E_{\mathrm{mat}}\in[10^{-2},10^{2}])$, where a strong-form PINN degrades to $5.58\%$, and its displacement error reaches $7.66\%$ against $0.49\%$ for the PI-GNN. A trained network halves the ($\sigma_{xx}$) error of an energy-based PINN ($5.01\%$ versus $10.94\%$). Training cost exceeds a single FE solve by more than an order of magnitude, so the construction is a variationally consistent, penalty-free interface representation for parametric surrogates and inverse identification rather than a replacement for a one-off FE analysis.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.LG).
Categorie arXiv: Numerical Analysis (math.NA) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.10983 — 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 2026-10-16T05:44:25.058Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).