A graph neural network parametrizes the material field in a fully differentiable topology optimization loop that enforces additive-manufacturing overhang and stress constraints, producing self-supporting designs without manual sensitivity derivation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Graph Neural Network-Based Topology Optimization for Self-Supporting Structures in Additive Manufacturing
A graph neural network parametrizes the material field in a fully differentiable topology optimization loop that enforces additive-manufacturing overhang and stress constraints, producing self-supporting designs without manual sensitivity derivation.