← Back to all news
arXiv Machine Learning By Weiyun Xu, Jiamu Liu

Growth-Inspired Graph Generation and Inverse Design of Mechanical Lattices via Dot Matrices Database Augmentation and GCNN

Read the original on arXiv Machine Learning →

This paper presents a morphogenetic graph‑generation framework that builds mechanical lattices by sequentially adding nodes from a discrete dot matrix, mirroring natural growth processes. The resulting 3D lattices are evaluated with finite‑element analysis and encoded as graphs, which a graph convolutional neural network (GCNN) uses to learn a topology‑property map and predict compressive stiffness. By coupling the GCNN surrogate with rapid sampling, the authors perform inverse design to achieve target stiffness values and extend the method to curved, nonlinear beams for shape‑programming applications.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jun 10

Non-linear mechanical field reconstruction coupling recurrent neural networks with physics-informed graph neural networks

arXiv:2606. 10909v1 Announce Type: cross Abstract: Reconstructing local stress fields in heterogeneous microstructures under non-linear, history-dependent loading remains a major computational bottleneck in multi-scale simulations.

By Manuel Ricardo Guevara Garban, Yves Chemisky, \'Etienne Pruli\`ere, Micha\"el Cl\'ement, Martin Abendroth, Bj\"orn Kiefer
More like this →
arXiv Machine Learning
Jul 21

Harnessing disorder to decouple extension and shear in kirigami metamaterials

arXiv:2607. 16583v1 Announce Type: cross Abstract: Kirigami turns stiff sheets into compliant, shape-morphing structures, but its reliance on periodic cut patterns comes at a cost: correlated panel rotations couple extension to shear, so stretching one axis drives a parasitic shear that cannot be suppressed, and also confine anisotropic stiffness to a narrow, discrete set of responses that cannot be tuned independently.

By Haomin Yu, Hanxun Jin, Mingxuan Bi, Mohammad Jafari, Feng Helen Long, Michael J Greenberg, Farid Alisafaei, Guy Genin
More like this →
arXiv Machine Learning
Jun 30

On Surrogate Modeling of Static Response of AM Short-Fiber Thermoplastics Using Graph Neural Networks

arXiv:2606. 28996v1 Announce Type: new Abstract: Short-fiber thermoplastic (SFT) composites are increasingly employed in lightweight aerospace and automotive structures owing to their favorable strength-to-weight ratio, high production rates, and recyclability.

By Pharindra Pathak (Auburn University, Oakridge National Lab, NASA Glenn Research Center, Auburn University, Auburn University), Vipin Kumar (Auburn University, Oakridge National Lab, NASA Glenn Research Center, Auburn University, Auburn University), Trenton M. Ricks (Auburn University, Oakridge National Lab, NASA Glenn Research Center, Auburn University, Auburn University), Suhasini Gururaja (Auburn University, Oakridge National Lab, NASA Glenn Research Center, Auburn University, Auburn University), Siddhartha Srivastava (Auburn University, Oakridge National Lab, NASA Glenn Research Center, Auburn University, Auburn University)
fine-tuning
More like this →
arXiv Machine Learning
Jun 18

A finite-element-inspired bipartite graph learned simulator for manufacturability assessment in large-deformation sheet forming

arXiv:2605. 22845v2 Announce Type: replace-cross Abstract: Explicit dynamic finite element (FE) simulations are widely used for large deformation engineering analysis, but repeated simulations remain costly during design space exploration and optimisation.

By Yingxue Zhao, Haoran Li, Haosu Zhou, Tobias Pfaff, Nan Li
ragbenchmarks
More like this →
arXiv AI
Sep 7

Data-Driven Discovery of Composition-Dependent Constitutive Models for Hyperelasticity and Viscoelasticity of Digital Materials

The paper introduces a data‑driven framework for modeling the hyperelastic and viscoelastic behavior of digital materials made by multi‑material 3D printing. It extends a classical constitutive formulation by Bergström and Boyce, preserving multiplicative kinematics and invariant‑based strain‑energy functions while learning equilibrium and nonequilibrium parameters from multi‑rate uniaxial compression data across different compositions. The approach can either predict closed‑form model parameters as functions of composition or construct polyconvex strain‑energy functions using neural ordinary differential equations, ensuring thermodynamic consistency and capturing rate‑dependent stiffness and hysteresis.

By Josu\'e Garc\'ia-\'Avila (Department of Mechanical Engineering, Columbia University, New York City, USA), Beijun Shen (Department of Mechanical Engineering, Columbia University, New York City, USA), Manuel K. Rausch (Department of Aerospace Engineering and Engineering Mechanics, University of Texas at Austin, Austin, USA, Department of Biomedical Engineering, University of Texas at Austin, Austin, USA, Department of Mechanical Engineering, University of Texas at Austin, Austin, USA), Mary C. Boyce (Department of Mechanical Engineering, Columbia University, New York City, USA), Adri\'an Buganza-Tepole (Department of Mechanical Engineering, Columbia University, New York City, USA)
More like this →