Hostname: page-component-586b7cd67f-t7fkt Total loading time: 0 Render date: 2024-11-22T04:54:30.955Z Has data issue: false hasContentIssue false
  • English
  • Français

ARTIFICIAL INTELLIGENCE TECHNIQUES FOR IMPROVING CYLINDRICAL SHRINK-FIT SHAFT-HUB COUPLINGS

Published online by Cambridge University Press:  19 June 2023

Muhammad Shahrukh Saeed ,
Jan Falter ,
Valesko Dausch ,
Markus Wagner ,
Matthias Kreimeyer  and
Boris Eisenbart
Muhammad Shahrukh Saeed*
Affiliation:
University of Stuttgart Swinburne University of Technology
Jan Falter
Affiliation:
University of Stuttgart
Valesko Dausch
Affiliation:
University of Stuttgart
Markus Wagner
Affiliation:
University of Stuttgart
Matthias Kreimeyer
Affiliation:
University of Stuttgart
Boris Eisenbart
Affiliation:
Swinburne University of Technology
*
Saeed, Muhammad Shahrukh, Swinburne University of Technology and 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.

Due to the continuous progress in information technology, complex problems of machine elements can be investigated using numerical methods. The focus of these investigations and optimizations often aims to reduce the stresses that occur or to increase the forces and torques that can be transmitted. Interference fit connections are an essential machine element for drive technology applications and are characterized by their economical fabrication. The transmission of external loads over a large contact surface between the shaft and hub makes it less vulnerable to impact loads. These advantages contrast with disadvantages such as the limited transmittable power, the risk of friction fatigue, and stress peaks at the hub edges, which can lead to undesirable and sudden failure, especially in the case of brittle hub materials. Analytical approaches already exist for optimizing these connections, which are expensive, time-consuming, and complex, so a high degree of expert knowledge is required to apply these methods in practice successfully. This paper presents a novel method using the example of optimizing the pressure distribution in the interface of a shrink-fit connection.

Keywords

Design engineeringArtificial intelligenceOptimisationIndustrial design
Type
Article
Information
Proceedings of the Design Society , Volume 3: ICED23 , July 2023 , pp. 645 - 656
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), 2023. Published by Cambridge University Press

References

Blacha, M. (2009), “Grundlagen zur Berechnung und Gestaltung von Querpressverbänden mit Naben aus monolithischer Keramik”, Doctoral, University of Stuttgart, 2009.Google Scholar
Dausch, V., Kröger, J. and Kreimeyer, M. (2022), “An AI-Based Approach to Optimize Stress in Shrink Fits”, Proceedings of the Design Society, Vol. 2, pp. 1549–1558.CrossRefGoogle Scholar
DIN 7190-1 (2017a), “Calculation and design rules for cylindrical self-locking pressfits. Interference fits – Part 1: Calculation and design rules for cylindrical self-locking pressfits”.Google Scholar
DIN7190-1 (2017b), “Calculation and design rules for cylindrical self-locking pressfits. Interference fits – Part 1: Calculation and design rules for cylindrical self-locking pressfits”.Google Scholar
DIN7190-2 (2017), “Calculation and design rules for conical self-locking pressfits. Interference fits – Part 2: Calculation and design rules for conical self-locking pressfits”.Google Scholar
Falter, J., Binz, H. and Kreimeyer, M. (Eds.) (2023), Investigations on design limits and improved material utilization of press-fit connections using elastic-plastic design.CrossRefGoogle Scholar
Falter, J., Dausch, V., Saeed, M.S., Binz, H. and Kreimeyer, M. (Eds.) (2022), Einsatz von KI-Methoden bei der Optimierung von Welle-Nabe-Verbindungen - Aufbau, funktion und Trainieren von KI-Methoden und künstlichen neuronalen Netzen: Gestaltung und Berechnung von Wellen mit Passverzahnungen, 2408, Leinfelden - Echterdingen, Stuttgart.CrossRefGoogle Scholar
Glöggler, C. (2003), Untersuchungen an spannungshomogenisierten und zylindrischen Pressverbindungen unter Torsionsbelastung.Google Scholar
Heydt, J.F. (2012), Untersuchungen zum dynamischen Verhalten von topologisch optimierten Pressverbänden bei Umlaufbiegung.Google Scholar
Kollmann, F.G. (1981), “Rotating Elasto-Plastic Interference Fits”, Journal of Mechanical Design, Vol. 103 No. 1, pp. 61–66.CrossRefGoogle Scholar
Krautter, M. and Binz, H. (Eds.) (2015), Improvement Of The Designing Method Of Hybrid Interference Fits.Google Scholar
Kröger, J. and Binz, H. (2020), Untersuchungen zu Auslegungsgrenzen und Steigerung der maximalen Übermaße bei zylindrischen Pressverbindungen: Abschlussbericht zum FVA-Forschungsvorhaben Nr. 810 I, Heft 1399.Google Scholar
Kröger, J., Binz, H. and Wagner, M. (2018), “Spannungsoptimierung von Pressverbänden mit additiv gefertigten Naben – Numerische und experimentelle Untersuchungen”, pp. 199–210.CrossRefGoogle Scholar
Leergaard Pedersen, N. (2022), “Optimal shaft-hub connections”, The Journal of Strain Analysis for Engineering Design, 030932472210800.CrossRefGoogle Scholar
Leidich, E. (Ed.) (2008), Welle-Nabe-Verbindungen 2008: Konstruktionselemente des Maschinenbaus 1, Springer, Berlin, Heidelberg.Google Scholar
Montague, P. (1999), “Reinforcement Learning: An Introduction, by Sutton, R.S. and Barto, A.G”, Trends in Cognitive Sciences, Vol. 3 No. 9, p. 360.CrossRefGoogle Scholar
Pedersen, N.L. (2016), “On optimization of interference fit assembly”, Structural and Multidisciplinary Optimization, Vol. 54 No. 2, pp. 349–359.CrossRefGoogle Scholar
Schwämmle, T. (2010), Betriebsverhalten von konventionellen und fugendruckhomogenisierten Pressverbänden unter Biegelast.Google Scholar
Skansi, S. (2018), Introduction to Deep Learning: From Logical Calculus to Artificial Intelligence, Undergraduate Topics in Computer Science, 1st ed. 2018, Springer International Publishing; Imprint: Springer, Cham.CrossRefGoogle Scholar
Smetana, T. (2001), Investigations on the transmission behavior of cone and cylinder press connections under bending loads.Google Scholar
Sutton, R.S. and Barto, A. (2018), Reinforcement learning: An introduction, Adaptive computation and machine learning, Second edition, The MIT Press, Cambridge, Massachusetts, London, England.Google Scholar
Wagner, M. and Binz, H. (2011), “Proof test of hybrid shrink fits with ceramic hub”, IOP Conference Series: Materials Science and Engineering, Vol. 18 No. 20, p. 202021.CrossRefGoogle Scholar
Wagner, M. and Binz, H. (2021), “Auslegung hybrider Querpressverbände für erhöhte Betriebstemperaturen”, Forschung im Ingenieurwesen, Vol. 85 No. 1, pp. 11–19.CrossRefGoogle Scholar
Womack, C. (2020), “Introduction to Artificial Intelligence and Machine Learning”.Google Scholar
Zhang, Y., McClain, B. and Fang, X.D. (2000), “Design of interference fits via finite element method”, International Journal of Mechanical Sciences, Vol. 42 No. 9, pp. 1835–1850.CrossRefGoogle Scholar