dc.contributor.advisor | Tomasz Wierzbicki. | en_US |
dc.contributor.author | Heidenreich, Julian,S.M.Massachusetts Institute of Technology. | en_US |
dc.contributor.other | Massachusetts Institute of Technology. Department of Mechanical Engineering. | en_US |
dc.date.accessioned | 2020-10-18T21:50:42Z | |
dc.date.available | 2020-10-18T21:50:42Z | |
dc.date.copyright | 2020 | en_US |
dc.date.issued | 2020 | en_US |
dc.identifier.uri | https://hdl.handle.net/1721.1/128086 | |
dc.description | Thesis: S.M., Massachusetts Institute of Technology, Department of Mechanical Engineering, 2020 | en_US |
dc.description | Cataloged from PDF of thesis. | en_US |
dc.description | Includes bibliographical references (pages 49-51). | en_US |
dc.description.abstract | During the past years, the neural networks drew more and more interest from the solid mechanics community. In particular, they have proven to provide a powerful framework for constitutive modeling. This work takes first tentative steps towards the use of convolutional neural network based modelling techniques to estimate structural response. The present work investigates the initial yield of two-dimensional architected materials. The dataset is obtained either by physical or virtual tests. In future applications, the network will be trained based on physical experiments. In the course of this work, they have been replaced by virtual experiments relying on numerical simulations. The computational framework is modeled as an encoder-decoder network and leverages the effectiveness of convolutional neural networks to estimate the structural response of two material structures. More specifically, the constructed network manages to replicate shape distortions of the yield surface for numerous hole configurations as well as various types of perforation. Furthermore, it accurately predicts the orientation dependent material response for varying degrees of anisotropy. The fact that the network directly translates geometrical data into mechanically significant quantities leads to the strong conjecture that structures. More specifically, the constructed network manages to replicate shape distortions of the yield surface for numerous hole configurations as well as various types of perforation. Furthermore, it accurately predicts the orientation dependent material response for varying degrees of anisotropy. The fact that the network directly translates geometrical data into mechanically significant quantities leads to the strong conjecture that. | en_US |
dc.description.statementofresponsibility | by Julian Heidenreich. | en_US |
dc.format.extent | 51 pages | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Massachusetts Institute of Technology | en_US |
dc.rights | MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided. | en_US |
dc.rights.uri | http://dspace.mit.edu/handle/1721.1/7582 | en_US |
dc.subject | Mechanical Engineering. | en_US |
dc.title | On the potential of convolutional neural networks for estimating the structural response of two-material structures | en_US |
dc.type | Thesis | en_US |
dc.description.degree | S.M. | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Department of Mechanical Engineering | en_US |
dc.identifier.oclc | 1200043039 | en_US |
dc.description.collection | S.M. Massachusetts Institute of Technology, Department of Mechanical Engineering | en_US |
dspace.imported | 2020-10-18T21:50:37Z | en_US |
mit.thesis.degree | Master | en_US |
mit.thesis.department | MechE | en_US |