Machine Learning Based Simulation for Design Space Exploration

DS 116: Proceedings of the DESIGN2022 17th International Design Conference

Year: 2022
Editor: Mario Štorga, Stanko Škec, Tomislav Martinec, Dorian Marjanović
Author: Oliver Bleisinger (1), Christian Malek (1), Stefan Holbach (2)
Series: DESIGN
Institution: 1: Fraunhofer IESE, Germany; 2: BorgWarner Turbo Systems Engineering GmbH, Germany
Section: Artificial Intelligence and Data-Driven Design
Page(s): 1521-1530
DOI number: https://doi.org/10.1017/pds.2022.154
ISSN: 2732-527X (Online)

Abstract

Design of software in the automotive domain often involves simulation to allow early software parametrization. Modeling complex systems or components impacted by the software in an analytical way can be time-consuming, require domain knowledge and executing the analytical models can result in high computational effort. In specific applications, these challenges can be overcome by applying machine learning based simulation. This contribution presents results of a case study in which powertrain components are modeled data-driven with artificial neural networks to support design space exploration

Keywords: artificial intelligence (AI), simulation-based design, data-driven design

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.