PC-NCLaws: Physics-Embedded Conditional Neural Constitutive Laws for Elastoplastic Materials

Simple item page
dc.contributor.authorXie, Xueguangen_US
dc.contributor.authorYan, Shuen_US
dc.contributor.authorJia, Shiwenen_US
dc.contributor.authorYang, Siyuen_US
dc.contributor.authorHao, Aiminen_US
dc.contributor.authorGao, Yangen_US
dc.contributor.authorYu, Pengen_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorHan, Ping-Hsuanen_US
dc.contributor.editorLin, Shih-Syunen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorSchneider, Teseoen_US
dc.contributor.editorTsai, Hsin-Rueyen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.contributor.editorZhang, Eugeneen_US
dc.date.accessioned2025-10-07T06:02:57Z
dc.date.available2025-10-07T06:02:57Z
dc.date.issued2025
dc.description.abstractWhile data-driven methods offer significant promise for modeling complex materials, they often face challenges in generalizing across diverse physical scenarios and maintaining physical consistency. To address these limitations, we propose a generalizable framework called Physics-Embedded Conditional Neural Constitutive Laws for Elastoplastic Materials, which combines the partial differential equations with neural networks. Specifically, the model employs two separate neural networks to model elastic and plastic constitutive laws. Simultaneously, the model incorporates physical parameters as conditional inputs and is trained on comprehensive datasets encompassing multiple scenarios with varying physical parameters, thereby enabling generalization across different properties without requiring retraining for each individual case. Furthermore, the differentiable architecture of our model, combined with its explicit parameter inputs, enables the inverse estimation of physical parameters from observed motion sequences. This capability extends our framework to objects with unknown or unmeasured properties. Experimental results demonstrate state-of-the-art performance in motion reconstruction, robust long-term prediction, geometry generalization, and precise parameters estimation for elastoplastic materials, highlighting its versatility as a unified simulator and inverse analysis tool.en_US
dc.description.sectionheadersPhysical Simulation
dc.description.seriesinformationPacific Graphics Conference Papers, Posters, and Demos
dc.identifier.doi10.2312/pg.20251266
dc.identifier.isbn978-3-03868-295-0
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20251266
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20251266
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Physical simulation
dc.subjectComputing methodologies → Physical simulation
dc.titlePC-NCLaws: Physics-Embedded Conditional Neural Constitutive Laws for Elastoplastic Materialsen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
pg20251266.pdf
Size:
4.09 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1195_mm1.mp4
Size:
70.21 MB
Format:
Video MP4
Download
Collections
PG2025 Conference Papers, Posters, and Demos