How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning

• URL: http://arxiv.org/abs/2111.05949v1
• Date: Wed, 10 Nov 2021 21:19:02 GMT
• Title: How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning
• Authors: Zhi Chen, Alexander Ogren, Chiara Daraio, L. Catherine Brinson, Cynthia Rudin
• Abstract summary: We develop a new interpretable, multi-resolution machine learning framework for finding patterns in the unit-cells of materials. Specifically, we propose two new interpretable representations of metamaterials, called shape-frequency features and unit-cell templates.
• Score: 82.67551367327634
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Metamaterials are composite materials with engineered geometrical micro- and meso-structures that can lead to uncommon physical properties, like negative Poisson's ratio or ultra-low shear resistance. Periodic metamaterials are composed of repeating unit-cells, and geometrical patterns within these unit-cells influence the propagation of elastic or acoustic waves and control dispersion. In this work, we develop a new interpretable, multi-resolution machine learning framework for finding patterns in the unit-cells of materials that reveal their dynamic properties. Specifically, we propose two new interpretable representations of metamaterials, called shape-frequency features and unit-cell templates. Machine learning models built using these feature classes can accurately predict dynamic material properties. These feature representations (particularly the unit-cell templates) have a useful property: they can operate on designs of higher resolutions. By learning key coarse scale patterns that can be reliably transferred to finer resolution design space via the shape-frequency features or unit-cell templates, we can almost freely design the fine resolution features of the unit-cell without changing coarse scale physics. Through this multi-resolution approach, we are able to design materials that possess target frequency ranges in which waves are allowed or disallowed to propagate (frequency bandgaps). Our approach yields major benefits: (1) unlike typical machine learning approaches to materials science, our models are interpretable, (2) our approaches leverage multi-resolution properties, and (3) our approach provides design flexibility.

Related papers

• Efficient Symmetry-Aware Materials Generation via Hierarchical Generative Flow Networks [52.13486402193811]
  New solid-state materials require rapidly exploring the vast space of crystal structures and locating stable regions. Existing methods struggle to explore large material spaces and generate diverse samples with desired properties and requirements. We propose a novel generative model employing a hierarchical exploration strategy to efficiently exploit the symmetry of the materials space to generate crystal structures given desired properties.
  arXiv  Detail & Related papers  (2024-11-06T23:53:34Z)
• Nonlinear Inverse Design of Mechanical Multi-Material Metamaterials Enabled by Video Denoising Diffusion and Structure Identifier [2.624762732763203]
  This paper presents a novel framework for inverse multi-material design based on nonlinear stress-strain responses. By incorporating multiple materials, plasticity, and large deformation, our innovative design method allows for enhanced control over the highly nonlinear mechanical behavior of metamaterials.
  arXiv  Detail & Related papers  (2024-09-20T21:26:15Z)
• Machine Learning-Guided Design of Non-Reciprocal and Asymmetric Elastic Chiral Metamaterials [0.0]
  This paper defines several design spaces for chiral metamaterials, including the ligament contact angles, the ligament shape, and circle radius. We then leverage machine learning approaches, and specifically Bayesian optimization, to determine optimally performing designs satisfying maximal non-reciprocity or stiffness asymmetry. Our analysis of the underlying mechanisms reveals that chiral metamaterials that can display multiple different contact states under loading in different directions are able to simultaneously exhibit both high non-reciprocity and stiffness asymmetry.
  arXiv  Detail & Related papers  (2024-04-19T23:39:56Z)
• Gradient-based Design of Computational Granular Crystals [0.22499166814992436]
  We build upon the similarity between thetemporal dynamics of wave propagation in material and the computational dynamics of Recurrent Neural Networks to develop a gradient-based optimization framework for harmonically driven granular crystals. Our findings show that a gradient-based optimization method can greatly expand the intrinsic design space of metamaterials.
  arXiv  Detail & Related papers  (2024-04-07T06:24:47Z)
• Guided Diffusion for Fast Inverse Design of Density-based Mechanical Metamaterials [41.97258566607252]
  This paper proposes a fast inverse design method, whose core is an advanced deep generative AI algorithm, to generate voxel-based mechanical metamaterials. Specifically, we use the self-conditioned diffusion model, capable of generating a microstructure with a resolution of $1283$ to approach the specified homogenized matrix in just 3 seconds.
  arXiv  Detail & Related papers  (2024-01-24T16:31:50Z)
• Scalable Diffusion for Materials Generation [99.71001883652211]
  We develop a unified crystal representation that can represent any crystal structure (UniMat) UniMat can generate high fidelity crystal structures from larger and more complex chemical systems. We propose additional metrics for evaluating generative models of materials.
  arXiv  Detail & Related papers  (2023-10-18T15:49:39Z)
• FAENet: Frame Averaging Equivariant GNN for Materials Modeling [123.19473575281357]
  We introduce a flexible framework relying on frameaveraging (SFA) to make any model E(3)-equivariant or invariant through data transformations. We prove the validity of our method theoretically and empirically demonstrate its superior accuracy and computational scalability in materials modeling.
  arXiv  Detail & Related papers  (2023-04-28T21:48:31Z)
• Dynamic Latent Separation for Deep Learning [67.62190501599176]
  A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
  arXiv  Detail & Related papers  (2022-10-07T17:56:53Z)
• A deep learning driven pseudospectral PCE based FFT homogenization algorithm for complex microstructures [68.8204255655161]
  It is shown that the proposed method is able to predict central moments of interest while being magnitudes faster to evaluate than traditional approaches. It is shown, that the proposed method is able to predict central moments of interest while being magnitudes faster to evaluate than traditional approaches.
  arXiv  Detail & Related papers  (2021-10-26T07:02:14Z)
• METASET: Exploring Shape and Property Spaces for Data-Driven Metamaterials Design [20.272835126269374]
  We show that a smaller yet diverse set of unit cells leads to scalable search and unbiased learning. Our flexible method can distill unique subsets regardless of the metric employed. Our diverse subsets are provided publicly for use by any designer.
  arXiv  Detail & Related papers  (2020-06-01T03:36:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.