• Featured in Physics

Machine Learning of Implicit Combinatorial Rules in Mechanical Metamaterials

Ryan van Mastrigt, Marjolein Dijkstra, Martin van Hecke, and Corentin Coulais
Phys. Rev. Lett. 129, 198003 – Published 2 November 2022
Physics logo See synopsis: Machine-Learning Tool Solves Metamaterial Jigsaw
PDFHTMLExport Citation

Abstract

Combinatorial problems arising in puzzles, origami, and (meta)material design have rare sets of solutions, which define complex and sharply delineated boundaries in configuration space. These boundaries are difficult to capture with conventional statistical and numerical methods. Here we show that convolutional neural networks can learn to recognize these boundaries for combinatorial mechanical metamaterials, down to finest detail, despite using heavily undersampled training sets, and can successfully generalize. This suggests that the network infers the underlying combinatorial rules from the sparse training set, opening up new possibilities for complex design of (meta)materials.

  • Figure
  • Figure
  • Figure
  • Figure
  • Received 8 February 2022
  • Accepted 14 September 2022

DOI:https://doi.org/10.1103/PhysRevLett.129.198003

© 2022 American Physical Society

Physics Subject Headings (PhySH)

Polymers & Soft Matter

synopsis

Key Image

Machine-Learning Tool Solves Metamaterial Jigsaw

Published 2 November 2022

A new tool can determine whether a collection of building blocks will assemble into a mechanically sound structure.

See more in Physics

Authors & Affiliations

Ryan van Mastrigt1,2,*, Marjolein Dijkstra3, Martin van Hecke2,4, and Corentin Coulais1

  • 1Institute of Physics, Universiteit van Amsterdam, Science Park 904, 1098 XH Amsterdam, The Netherlands
  • 2AMOLF, Science Park 104, 1098 XG Amsterdam, The Netherlands
  • 3Soft Condensed Matter, Debye Institute for Nanomaterials Science, Department of Physics, Utrecht University, Princetonplein 5, 3584 CC Utrecht, The Netherlands
  • 4Huygens-Kamerling Onnes Lab, Universiteit Leiden, Postbus 9504, 2300 RA Leiden, The Netherlands

  • *r.vanmastrigt@uva.nl

Article Text (Subscription Required)

Click to Expand

Supplemental Material (Subscription Required)

Click to Expand

References (Subscription Required)

Click to Expand
Issue

Vol. 129, Iss. 19 — 4 November 2022

Reuse & Permissions
Access Options
Author publication services for translation and copyediting assistance advertisement

Authorization Required


×
×

Images

×

Sign up to receive regular email alerts from Physical Review Letters

Log In

Cancel
×

Search


Article Lookup

Paste a citation or DOI

Enter a citation
×