NTopo: Mesh-free Topology Optimization using Implicit Neural Representations

TL;DR

This paper introduces NTopo, a mesh-free topology optimization method using implicit neural representations, enabling continuous, differentiable solutions for structural design problems with competitive performance.

Contribution

It presents a novel neural network-based approach for mesh-free topology optimization, leveraging implicit neural representations for high-dimensional inverse problems.

Findings

Highly competitive in minimizing structural compliance

Enables self-supervised learning of continuous solutions

Demonstrates effectiveness of neural representations in topology optimization

Abstract

Recent advances in implicit neural representations show great promise when it comes to generating numerical solutions to partial differential equations. Compared to conventional alternatives, such representations employ parameterized neural networks to define, in a mesh-free manner, signals that are highly-detailed, continuous, and fully differentiable. In this work, we present a novel machine learning approach for topology optimization -- an important class of inverse problems with high-dimensional parameter spaces and highly nonlinear objective landscapes. To effectively leverage neural representations in the context of mesh-free topology optimization, we use multilayer perceptrons to parameterize both density and displacement fields. Our experiments indicate that our method is highly competitive for minimizing structural compliance objectives, and it enables self-supervised learning of continuous solution spaces for topology optimization problems.