Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation
This work addresses the problem of accelerating design processes in engineering, particularly for structural topology optimization, by enhancing generative models to handle constraints more effectively, though it appears incremental as it builds on existing diffusion and optimization methods.
The paper tackled the challenge of using generative models for constrained design in engineering, where data is scarce and precision is key, by introducing Diffusion Optimization Models (DOM) and Trajectory Alignment (TA) to align diffusion model sampling with physics-based optimization trajectories. The result showed that TA outperforms state-of-the-art deep generative models on in-distribution configurations, halves inference computational cost, and improves manufacturability for out-of-distribution conditions with few optimization steps.
Generative models have had a profound impact on vision and language, paving the way for a new era of multimodal generative applications. While these successes have inspired researchers to explore using generative models in science and engineering to accelerate the design process and reduce the reliance on iterative optimization, challenges remain. Specifically, engineering optimization methods based on physics still outperform generative models when dealing with constrained environments where data is scarce and precision is paramount. To address these challenges, we introduce Diffusion Optimization Models (DOM) and Trajectory Alignment (TA), a learning framework that demonstrates the efficacy of aligning the sampling trajectory of diffusion models with the optimization trajectory derived from traditional physics-based methods. This alignment ensures that the sampling process remains grounded in the underlying physical principles. Our method allows for generating feasible and high-performance designs in as few as two steps without the need for expensive preprocessing, external surrogate models, or additional labeled data. We apply our framework to structural topology optimization, a fundamental problem in mechanical design, evaluating its performance on in- and out-of-distribution configurations. Our results demonstrate that TA outperforms state-of-the-art deep generative models on in-distribution configurations and halves the inference computational cost. When coupled with a few steps of optimization, it also improves manufacturability for out-of-distribution conditions. By significantly improving performance and inference efficiency, DOM enables us to generate high-quality designs in just a few steps and guide them toward regions of high performance and manufacturability, paving the way for the widespread application of generative models in large-scale data-driven design.