Session: DAC-04-2: Data-Driven Design

Paper Number: 142052

142052 - To Quantize or Not to Quantize: Effects on Generative Models for 2D Heat Sink Design 

In Topology Optimization (TO) and related engineering applications, physics-constrained simulations are often used to optimize candidate designs given some set of boundary conditions. However, such models are computationally expensive and do not guarantee convergence to a desired result, given the frequent nonconvexity of the performance objective. Creating data-based approaches to warm-start these models—or even replace them entirely—has thus been a top priority for researchers in this area of engineering design. In this paper, we present a new dataset of two-dimensional heat sink designs optimized via Multiphysics Topology Optimization (MTO). Further, we propose an augmented Vector-Quantized GAN (VQGAN) that allows for effective MTO data compression within a discrete latent space, known as a codebook, while preserving high reconstruction quality. To concretely assess the benefits of the VQGAN quantization process, we conduct a latent analysis of its codebook as compared to the continuous latent space of a deep AutoEncoder (AE). We find that VQGAN can more effectively learn topological connections despite a high rate of data compression. Finally, we leverage the VQGAN codebook to train a small GPT-2 model, generating thermally performant heat sink designs within a fraction of the time taken by conventional optimization approaches. We show the transformer-based approach is more effective than using a Deep Convolutional GAN (DCGAN) due to its elimination of mode collapse issues, as well as better preservation of topological connections in MTO and similar applications.

Presenting Author: Arthur Drake University of Maryland, College Park

Presenting Author Biography: Arthur Drake is currently a Ph.D. student at the University of Maryland, College Park. He is researching in the area of generative models in machine learning to build on previous design optimization work. He received his B.S. in Mechanical Engineering from UMD in December 2020.

Authors:

Arthur Drake University of Maryland, College Park
Jun Wang Santa Clara University
Qiuyi Chen University of Maryland, College Park
Ardalan Nejat Johns Hopkins University
James Guest Johns Hopkins University
Mark Fuge University of Maryland, College Park