Graph neural network-based algorithm for design optimization of truss structures

doi:10.1016/j.istruc.2026.113145

Graph neural network-based algorithm for design optimization of truss structures

2026-09-30

0

PRE

AI

DOI：10.1016/j.istruc.2026.113145

Original

Original request for help

Save

Abstract

En 中文

A novel Graph Neural Network (GNN)-based algorithm for design optimization of truss structures is proposed in this paper presents through a combination of Multi-head Attention (MHA) mechanism and a newly developed hybrid adaptive sampling strategy. The algorithm involves the generation of high-fidelity training datasets employing Finite Element Analysis (FEA) to establish a Graph Attention Network (GAT) surrogate model, the approximation of objective or constraint functions by the trained GAT model, and the solution of structural optimization problems using the Particle Swarm Optimization (PSO) algorithm. As a result, the GAT surrogate model dramatically reduces the number of required high-fidelity training datasets, and shows a strong ability to approximate the objective or constraint functions, thereby enabling accurate estimation of the optimum solution. It is shown through two numerical examples on truss structures that the proposed algorithm provides accurate and computationally efﬁcient estimates of the solutions of structural optimization problems.

Keywords:

Structural optimization

Surrogate model

Graph attention network

Finite element method

Particle swarm optimization

Objective function

Graph neural network-based algorithm for design optimization of truss structures

Abstract

Journal

Organization

Cited Papers