Latent Diffusion Models for Structural Component Design

TL;DR

This paper introduces a Latent Diffusion model-based framework for generative structural component design, capable of producing near-optimal, editable designs satisfying specific loading conditions, with demonstrated scalability and performance.

Contribution

It presents a novel application of Latent Diffusion models for structural design, enabling design generation and editing based on topology optimization data.

Findings

Generates near-optimal structural designs satisfying loading conditions

Supports editing of existing designs

Operates effectively over voxel resolutions from 32^3 to 128^3

Abstract

Recent advances in generative modeling, namely Diffusion models, have revolutionized generative modeling, enabling high-quality image generation tailored to user needs. This paper proposes a framework for the generative design of structural components. Specifically, we employ a Latent Diffusion model to generate potential designs of a component that can satisfy a set of problem-specific loading conditions. One of the distinct advantages our approach offers over other generative approaches, such as generative adversarial networks (GANs), is that it permits the editing of existing designs. We train our model using a dataset of geometries obtained from structural topology optimization utilizing the SIMP algorithm. Consequently, our framework generates inherently near-optimal designs. Our work presents quantitative results that support the structural performance of the generated designs and the variability in potential candidate designs. Furthermore, we provide evidence of the scalability of our framework by operating over voxel domains with resolutions varying from $32^3$ to $128^3$. Our framework can be used as a starting point for generating novel near-optimal designs similar to topology-optimized designs.