A Machine Learning-Based Approach for Quick Evaluation of Live Simulations in Embodiment Design

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

Year: 2022
Editor: Mario Štorga, Stanko Škec, Tomislav Martinec, Dorian Marjanović
Author: Christopher Sauer (1), Benjamin Gersch
Series: DESIGN
Institution: 1: Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany; 2: CADFEM GmbH, Germany
Section: Artificial Intelligence and Data-Driven Design
Page(s): 1757-1766
DOI number: https://doi.org/10.1017/pds.2022.178
ISSN: 2732-527X (Online)

Abstract

Supporting product developers in early design phases with Live-Simulation can enhance the quality of early product designs. Live-Simulation can also facilitate a democratization of simulation and puts away pressure from simulation experts. In this paper, a machine learning based quick evaluation tool is proposed to support product developers in interpreting Live-Simulation results. The proposed tool enables a quick evaluation of the Live-Simulation results and enables product developers to further enhance their simulations. The tool is shown within a use case in bike rocker switch design.

Keywords: data-driven design, simulation-based design, structural analysis, machine learning, live-simulation