Growth-Inspired Graph Generation and Inverse Design of Mechanical Lattices via Dot Matrices Database Augmentation and GCNN
Summary
This paper presents a graph-generation framework for designing 3D mechanical lattices, inspired by biological growth, which uses a GCNN for inverse design to achieve target mechanical properties.
View Cached Full Text
Cached at: 09/25/26, 09:41 AM
# Growth-Inspired Graph Generation and Inverse Design of Mechanical Lattices via Dot Matrices Database Augmentation and GCNN Source: [https://arxiv.org/abs/2609.29024](https://arxiv.org/abs/2609.29024) [View PDF](https://arxiv.org/pdf/2609.29024) > Abstract:Natural load\-bearing and transport networks are not assembled in a single step; they emerge through a temporally ordered process of growth, branching, reinforcement, and loop formation\. Inspired by this developmental logic, this work introduces a morphogenetic graph\-generation framework for mechanical lattices in which a discrete dot matrix provides potential nodes and the final architecture is created by sequential cross\-layer and intra\-layer growth\. The same rule is visualized in two dimensions as a leaf\-vein\-like developmental sequence and implemented in three dimensions on a 3x3x3 nodal matrix containing 27 candidate nodes\. A dataset of distinct three\-dimensional lattices was evaluated by beam\-based finite element analysis and represented directly as graphs\. A graph convolutional neural network \(GCNN\) with three graph\-convolution layers and dual global pooling learns the topology\-property mapping and predicts effective compressive stiffness\. Coupling the GCNN surrogate with rapid structural sampling enables inverse design: for a target stiffness of 1000 MPa, the selected design was predicted at 1042\.43 MPa and validated by finite element analysis at 1027\.49 MPa\. Beyond straight members, the framework has also been extended to parameterized horseshoe\-shaped curved beams made of nonlinear materials, enabling topology\-geometry design toward prescribed deformation shapes\. Our work provides a paradigm for augmenting the database of mechanical metamaterials, and the resulting perspective links biological morphogenesis, graph learning, and nonlinear shape programming in a unified generative design framework for architected materials\. ## Submission history From: Weiyun Xu \[[view email](https://arxiv.org/show-email/50277340/2609.29024)\] **\[v1\]**Thu, 24 Sep 2026 04:46:32 UTC \(1,007 KB\)
Similar Articles
Scaling Novel Graph Generation via Lightweight Structure-Guided Autoregressive Models
Researchers propose a lightweight autoregressive framework for graph generation that uses structure-guided topological ordering to achieve near log-linear complexity, addressing scalability and novelty limitations of existing diffusion and autoregressive methods. The approach supports both LSTM and Mamba-style backbones and shows improved novelty while maintaining validity and uniqueness on molecular and non-molecular benchmarks.
Learning coarse-step dynamics and internal mechanical response with graph networks
Introduces Newmark-β-DGN, a graph neural network framework that infers internal mechanical responses from coarse-step motion observations, enabling long-horizon prediction and analysis of forces without direct supervision.
Mesh-Native Physics-Informed Graph Surrogates for TCAD-in-the-Loop Design Space Exploration
A physics-informed graph attention network is proposed as a surrogate for TCAD simulation, enabling faster design space exploration by predicting mesh-node values and incorporating carrier-transport physics.
Repurposing 3D Generative Model for Autoregressive Layout Generation
LaviGen is a framework that repurposes 3D generative models for autoregressive 3D layout generation, using an adapted 3D diffusion model with dual-guidance self-rollout distillation to achieve 19% higher physical plausibility and 65% faster computation than state-of-the-art methods on the LayoutVLM benchmark.
Reinforcement learning for inverse structural design and rapid laser cutting of kirigami prototypes
This paper introduces RL-Kirigami, a framework combining optimal-transport conditional flow matching and reinforcement learning to solve the inverse design problem for kirigami metamaterials, achieving high accuracy and enabling rapid laser-cut prototype fabrication.