Diffusion Models Beat GANs on Topology Optimization

TL;DR

This paper introduces TopoDiff, a diffusion-model-based approach for topology optimization that outperforms GANs by producing more feasible structures with better mechanical performance, offering a new framework for engineering design synthesis.

Contribution

The paper presents TopoDiff, a novel diffusion-model-based architecture for topology optimization that improves performance and manufacturability over GAN-based methods.

Findings

Reduces average error on physical performance by a factor of eight.

Produces eleven times fewer infeasible samples.

Outperforms state-of-the-art conditional GANs in topology optimization.

Abstract

Structural topology optimization, which aims to find the optimal physical structure that maximizes mechanical performance, is vital in engineering design applications in aerospace, mechanical, and civil engineering. Generative adversarial networks (GANs) have recently emerged as a popular alternative to traditional iterative topology optimization methods. However, these models are often difficult to train, have limited generalizability, and due to their goal of mimicking optimal structures, neglect manufacturability and performance objectives like mechanical compliance. We propose TopoDiff - a conditional diffusion-model-based architecture to perform performance-aware and manufacturability-aware topology optimization that overcomes these issues. Our model introduces a surrogate model-based guidance strategy that actively favors structures with low compliance and good manufacturability. Our method significantly outperforms a state-of-art conditional GAN by reducing the average error on physical performance by a factor of eight and by producing eleven times fewer infeasible samples. By introducing diffusion models to topology optimization, we show that conditional diffusion models have the ability to outperform GANs in engineering design synthesis applications too. Our work also suggests a general framework for engineering optimization problems using diffusion models and external performance with constraint-aware guidance. We publicly share the data, code, and trained models here: https://decode.mit.edu/projects/topodiff/.