Forward and Inverse Design of Kirigami via Supervised Autoencoder

Abstract

Machine learning (ML) methods have recently been used as forward solvers to predict the mechanical properties of composite materials. Here, we use a supervised-autoencoder (sAE) to perform inverse design of graphene kirigami, where predicting the ultimate stress or strain under tensile loading is known to be difficult due to nonlinear effects arising from the out-of-plane buckling. Unlike the standard autoencoder, our sAE is able not only to reconstruct cut configurations but also to predict mechanical properties of graphene kirigami and classify the kirigami witheither parallel or orthogonal cuts. By interpolating in the latent space of kirigami structures, the sAE is able to generate novel designs that mix parallel and orthogonal cuts, despite being trained independently on parallel or orthogonal cuts. Our method allows us to both identify novel designs and predict, with reasonable accuracy, their mechanical properties, which is crucial for expanding the search space for materials design.

References in corpus (17)

• Automatic chemical design using a data-driven continuous representation of molecules
• A high-bias, low-variance introduction to Machine Learning for physicists
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Discovery of low thermal conductivity compounds with first-principles anharmonic lattice dynamics calculations and Bayesian optimization
• Buckling-Induced Kirigami
• Accelerated search and design of stretchable graphene kirigami using machine learning
• Polarization and valley switching in monolayer group-IV monochalcogenides
• Highly Deformable Graphene Kirigami
• Kirigami Actuators
• Multistable Kirigami for Tunable Architected Materials
• Highly Stretchable MoS${}_2$ Kirigami
• Piezoelectricity and valley Chern number in inhomogeneous hexagonal 2D crystals
• Two-dimensional Square Buckled Rashba Lead Chalcogenides
• Kirigami mechanics as stress relief by elastic charges
• Strain-induced gauge and Rashba fields in ferroelectric Rashba lead chalcogenide PbX monolayers (X = S, Se, Te)
• Valley notch filter in a graphene strain superlattice: Green's function and machine learning approach
• Nonlinear mechanics of thin frames

Cited by in corpus (10)

• Tailoring Structure-borne Sound Through Bandgap Engineering in Phononic Crystals and Metamaterials: A Comprehensive Review
• Machine Learning of Implicit Combinatorial Rules in Mechanical Metamaterials
• Towards out of distribution generalization for problems in mechanics
• An Interpretable Machine Learning Model for Deformation of Multi-Walled Carbon Nanotubes
• Anomalous thermal expansion in Ising-like puckered sheets
• Deep learning Local Reduced Density Matrices for Many-body Hamiltonian Estimation
• Vibrations and tunneling of strained nanoribbons at finite temperature
• Exploring fundamental laws of classical mechanics via predicting the orbits of planets based on neural networks
• Learning crystal field parameters using convolutional neural networks
• Learning Mechanically Driven Emergent Behavior with Message Passing Neural Networks