Constrained Multi-Objective Design Optimization in Systems Engineering Using Active Learning

DS 130: Proceedings of NordDesign 2024, Reykjavik, Iceland, 12th - 14th August 2024

Year: 2024
Editor: Malmqvist, J.; Candi, M.; Saemundsson, R. J.; Bystrom, F. and Isaksson, O.
Author: Bleisinger, Oliver; Keil, Mareike; Eigner, Martin
Series: NordDESIGN
Institution: University of Kaiserslautern-Landau, Germany; University of Mannheim, Germany; EIGNER engineering consult, Germany
Page(s): 352-361
DOI number: 10.35199/NORDDESIGN2024.38
ISBN: 978-1-912254-21-7

Abstract

Design of complex systems demands exploration of high-dimensional design spaces due to competing design goals and numerous design parameters. Manual tradeoff studies in hyperspaces are laborious and hence, Artificial Intelligence offers a solution. This paper introduces a Constrained Multi-Objective Design Optimization approach in Systems Engineering using Artificial Intelligence and evaluates this method through an automotive case study. Therefore, an Active Learning algorithm is presented to automate identifying pareto fronts by inferring simulation models as substitution for learning data.

Keywords: Artificial Intelligence (AI), Machine Learning (ML), Systems Engineering (SE), Design Optimisation, Simulation Based Design

Download

Please sign in to your account

This site uses cookies and other tracking technologies to assist with navigation and your ability to provide feedback, analyse your use of our products and services, assist with our promotional and marketing efforts, and provide content from third parties. Privacy Policy.