An AI-Based Approach to Optimize Stress in Shrink Fits

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

Year: 2022
Editor: Mario Štorga, Stanko Škec, Tomislav Martinec, Dorian Marjanović
Author: Valesko Dausch, Jan Kr
Series: DESIGN
Institution: University of Stuttgart, Germany
Section: Artificial Intelligence and Data-Driven Design
Page(s): 1549-1558
DOI number: https://doi.org/10.1017/pds.2022.157
ISSN: 2732-527X (Online)

Abstract

The present analytical design of shrink fits typically results in an uneven stress condition that can lead to failure in a variety of manners. With increasing loads and the use of brittle materials, the optimization of the stresses in the shrink fit hence becomes increasingly necessary. Currently existing approaches do not solve the problem satisfactorily or increase the manufacturing and design effort. This paper therefore considers the implementation of an AI-based stress optimization using reinforcement learning, which performs stress optimization by geometrically contouring the interstice.

Keywords: artificial intelligence (AI), engineering design, numerical methods, optimisation, structural analysis

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.