Graph Neural Network-Based Topology Optimization for Self-Supporting Structures in Additive Manufacturing

2025-08-26

AI Summary

Topology optimization for additive manufacturing (AM) faces challenges in ensuring self-supporting structures while satisfying mechanical performance requirements. Method: This paper proposes an end-to-end differentiable machine learning framework: a graph neural network (GNN) operates directly on finite-element meshes to predict continuous material distributions; a differentiable AM filter explicitly removes overhanging regions to guarantee printability; and a differentiable p-norm stress aggregation, combined with automatic differentiation, unifies geometric filtering and stress constraints—eliminating the need for manual sensitivity derivation. Contribution/Results: The fully differentiable architecture jointly optimizes structural performance (subject to volume and stress constraints) and manufacturability (self-supporting geometry, minimal post-processing). Experiments demonstrate stable generation of high-performance, AM-ready designs across multiple loading conditions, significantly improving design reliability and robustness compared to conventional approaches.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Mixed Discrete/Continuous Search
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This paper presents a machine learning-based framework for topology optimization of self-supporting structures, specifically tailored for additive manufacturing (AM). By employing a graph neural network (GNN) that acts as a neural field over the finite element mesh, the framework effectively learns and predicts continuous material distributions. An integrated AM filter ensures printability by eliminating unsupported overhangs, while the optimization process minimizes structural compliance under volume and stress constraints. The stress constraint is enforced using a differentiable p-norm aggregation of von Mises stress, promoting mechanical reliability in the optimized designs. A key advantage of the approach lies in its fully differentiable architecture, which leverages automatic differentiation throughout the optimization loop--eliminating the need for explicit sensitivity derivation for both the filter and the stress constraint. Numerical experiments demonstrate the ability of the framework to generate stress-constrained manufacturable topologies under various loading and boundary conditions, offering a practical pathway toward AM-ready high-performance designs with reduced post-processing requirements.

Problem

• Optimizing self-supporting structures for additive manufacturing
• Enforcing stress constraints to ensure mechanical reliability
• Eliminating unsupported overhangs through integrated AM filter

Innovation

• Graph Neural Network predicts material distributions
• Differentiable p-norm aggregation enforces stress constraints
• Integrated AM filter ensures structural printability