On Diverse System-Level Design Using Manifold Learning and Partial Simulated Annealing
DS 116: Proceedings of the DESIGN2022 17th International Design Conference
Year: 2022
Editor: Mario Štorga, Stanko Škec, Tomislav Martinec, Dorian Marjanović
Author: Adam Cobb, Anirban Roy, Daniel Elenius, Kaushik Koneripalli, Susmit Jha
Series: DESIGN
Institution: SRI International, United States of America
Section: Artificial Intelligence and Data-Driven Design
Page(s): 1541-1548
DOI number: https://doi.org/10.1017/pds.2022.156
ISSN: 2732-527X (Online)
Abstract
The goal in system-level design is to generate a diverse set of high-performing design configurations that allow trade-offs across different objectives and avoid early concretization. We use deep generative models to learn a manifold of the valid design space, followed by Monte Carlo sampling to explore and optimize design over the learned manifold, producing a diverse set of optimal designs. We demonstrate the efficacy of our proposed approach on the design of an SAE race vehicle and propeller.
Keywords: artificial intelligence (AI), engineering design, cyber-physical systems