Hostname: page-component-cd9895bd7-8ctnn Total loading time: 0 Render date: 2024-12-26T21:36:52.706Z Has data issue: false hasContentIssue false
  • English
  • Français

An AI-Based Approach to Optimize Stress in Shrink Fits

Published online by Cambridge University Press:  26 May 2022

V. Dausch ,
J. Kröger  and
M. Kreimeyer
V. Dausch
Affiliation:
University of Stuttgart, Germany
J. Kröger*
Affiliation:
University of Stuttgart, Germany
M. Kreimeyer
Affiliation:
University of Stuttgart, Germany
*
[email protected]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

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 designnumerical methodsoptimisationstructural analysis
Type
Article
Information
Proceedings of the Design Society , Volume 2: DESIGN2022 , May 2022 , pp. 1549 - 1558
Creative Commons
Creative Common License - CCCreative Common License - BYCreative Common License - NCCreative Common License - ND
This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives licence (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is unaltered and is properly cited. The written permission of Cambridge University Press must be obtained for commercial re-use or in order to create a derivative work.
Copyright
The Author(s), 2022.

References

Ayodele, T. O. (2010), “Machine Learning Overview”, In: Zhang, Y. (Ed.), “New Advances in Machine Learning”, IntechOpen, Rijeka, pp. 9–18. 10.5772/225Google Scholar
Blacha, M. (2009), “Grundlagen zur Berechnung und Gestaltung von Querpressverbänden mit Naben aus monolithischer Keramik”, PhD thesis, University of Stuttgart.Google Scholar
Cunningham, P., Cord, M., Delany, S. J. (2008), “Supervised Learning”, In: Cord, M., Cunningham, P. (Eds.), “Machine Learning Techniques for Mulitmedia: Case Studies on Organization an Retrieval”, Springer, Berlin, pp. 21–49. 10.1007/978-3-540-75171-7_2Google Scholar
DIN (2017), DIN 7190-1:2017-02, “Pressverbände - Teil 1: Berechnungsgrundlagen und Gestaltungsregeln für zylindrische Pressverbände”, Beuth Verlag GmbH, Berlin.Google Scholar
European Parliament (2020), “Was ist künstliche Intelligenz und wie wird sie genutzt?”, [online] https://www.europarl.europa.eu/news/de/headlines/society/20200827STO85804/was-ist-kunstliche-intelligenz-und-wie-wird-sie-genutzt [retrieved on 09.11.2021].Google Scholar
Goodfellow, I.; Bengio, Y. & Courville, A. (2016), “Deep Learning”, MIT Press.Google Scholar
Glöggler, C. (2003), “Untersuchungen an spannungshomogenisierten und zylindrischen Pressverbindungen unter Torsionsbelastung”, PhD thesis, University of Stuttgart.Google Scholar
Gropp, H., Ziaei, M. (2012), “Tendenzielle Ermittlung von zulässigen Werten für das erweiterte Ruiz-Chen-Kriterium bei reibdauerbeanspruchten torsionsbelasteten Pressverbindungen”, VDI-Berichte vol. 2176, Düsseldorf, pp. 37–47.Google Scholar
Hartmann, M. (1999), “Konstruieren mit Keramik: Ohne Ecken und Kanten”, Industrieanzeiger Nr. 5.Google Scholar
IBM (2020), “Unsupervised Learning”, [online] https://www.ibm.com/cloud/learn/unsupervised-learning [retrieved on 09.11.2021]Google Scholar
Kollmann, F. G. (1984), “Welle-Nabe-Verbindungen: Gestaltung, Auslegung, Auswahl”, Springer, Berlin. 10.1007/978-3-642-61727-0Google Scholar
Krautter, M., Binz, H. (2015), “Improvement Of The Designing Method Of Hybrid Interference Fits” NAFEMS World Congress, 2nd International SPDM Conference, San Diego.Google Scholar
Kröger, J., Binz, H. (2018), “Spannungsoptimierung von Pressverbänden mit additiv gefertigten Naben: Numerische und experimentelle Untersuchungen”, VDI-Berichte vol. 2337, Stuttgart, pp. 199–210.CrossRefGoogle Scholar
Kröger, J., Binz, H. (2020), “Hohe Übermaße bei Pressverbindungen: Untersuchungen zu Auslegungsgrenzen und Steigerung der maximalen Übermaße bei zylindrischen Pressverbindungen”, FVA Research Booklet 1399 and related information sheet, Frankfurt.Google Scholar
Leidich, E. (1983), “Beanspruchung von Pressverbindungen im elastischen Bereich und Auslegung gegen Dauerbruch”, PhD thesis, TH Darmstadt.Google Scholar
Mather, J., Baines, B. H. (1972), “Distribution of stress in axially symmetric shrink-fit assemblies”, Wear 21, pp. 339–360.CrossRefGoogle Scholar
Mitchell, T. M. (1997), “Machine Learning”, McGraw-Hill, New York.Google Scholar
Nasteski, V. (2017), “An overview of the supervised machine learning methods”, HORIZONS. B. 4, pp. 51–62.Google Scholar
Rentzsch, W. H., Willmann, G. (2002), “Ein einfaches Hilfsmittel zum Konstruieren mit Keramik”, In: “Materials Science & Engineering Technology”, vol. 33, pp. 184–189.Google Scholar
Skansi, S. (2018), “Introduction to Deep Learning: From Logical Calculus to Artificial Intelligence”, In: Mackie, I. (Ed.), “Undergraduate Topics in Computer Science”, Springer. 10.1007/978-3-319-73004-2CrossRefGoogle Scholar
Sutton, R. S. & Barto, A. G. (2018), “Reinforcement Learning: An Introduction”, The MIT Press.Google Scholar
Tokic, M. (2010) “Adaptive ε-Greedy Exploration in Reinforcement Learning Based on Value Differences”, In: Dillmann, R., Beyerer, J., Hanebeck, U.D. and Schultz, T. (Eds.), KI 2010: Advances in Artificial Intelligence, 2010, Berlin, Heidelberg, Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 203–210. 10.1007/978-3-642-16111-7_23CrossRefGoogle Scholar
Ulrich, D., Binz, H. (2016), “Einfluss von Schmierstoffen aus der Massivumformtechnik auf die Reibdauerbeanspruchung mikroschlupfanfälliger Welle-Nabe-Verbindungen: Numerische und experimentelle Untersuchungen anhand zylindrischer Querpressverbände mit beschichteten Wellen unter wechselnder Torsionslast”, VDI-Berichte vol. 2287, Karlsruhe, pp. 65–78.Google Scholar
Vidner, J., (2016) “Methode zur Bewertung der Ermüdungsfestigkeit von reibdauerbeanspruchten Systemen”, PhD thesis, TU Chemnitz.Google Scholar