Latent Diffusion Models for Structural Component Design
This work addresses the need for efficient and editable generative design in engineering, offering a scalable tool for creating near-optimal structural components, though it is incremental as it applies existing diffusion models to a new domain.
The paper tackles the problem of generative design for structural components by proposing a Latent Diffusion model framework that generates near-optimal designs satisfying specific loading conditions, with quantitative results showing structural performance and scalability up to 128^3 voxel resolutions.
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.