HeatGen: A Guided Diffusion Framework for Multiphysics Heat Sink Design Optimization

TL;DR

HeatGen introduces a guided diffusion framework that efficiently generates heat sink designs optimizing for low pressure drop and temperature constraints, outperforming traditional methods in scalability and computational cost.

Contribution

This work develops a novel guided diffusion model for heat sink design, integrating surrogate gradients for constraint satisfaction, and demonstrating superior performance over traditional optimization techniques.

Findings

Generated designs achieve up to 10% lower pressure drops.

The method is scalable with sufficient training data.

Inference is computationally inexpensive once trained.

Abstract

This study presents a generative optimization framework based on a guided denoising diffusion probabilistic model (DDPM) that leverages surrogate gradients to generate heat sink designs minimizing pressure drop while maintaining surface temperatures below a specified threshold. Geometries are represented using boundary representations of multiple fins, and a multi-fidelity approach is employed to generate training data. Using this dataset, along with vectors representing the boundary representation geometries, we train a denoising diffusion probabilistic model to generate heat sinks with characteristics consistent with those observed in the data. We train two different residual neural networks to predict the pressure drop and surface temperature for each geometry. We use the gradients of these surrogate models with respect to the design variables to guide the geometry generation process toward satisfying the low-pressure and surface temperature constraints. This inference-time guidance directs the generative process toward heat sink designs that not only prevent overheating but also achieve lower pressure drops compared to traditional optimization methods such as CMA-ES. In contrast to traditional black-box optimization approaches, our method is scalable, provided sufficient training data is available. Unlike traditional topology optimization methods, once the model is trained and the heat sink world model is saved, inference under new constraints (e.g., temperature) is computationally inexpensive and does not require retraining. Samples generated using the guided diffusion model achieve pressure drops up to 10 percent lower than the limits obtained by traditional black-box optimization methods. This work represents a step toward building a foundational generative model for electronics cooling.