☆ 4.7 Article

End-to-end three-dimensional designing of complex disordered materials from limited data using machine learning

PHYSICAL REVIEW E (2022)

Related references

Note: Only part of the references are listed.

Article Engineering, Mechanical

Understanding the microstructure behaviour of the Li-ion battery separator under compression using 3D image-based modelling

Wei Sun et al.

Summary: A 3D image-based modelling method was used to predict the compressive behavior of Li-ion battery separators. The microstructure of the solid PP phase was obtained by image segmentation, and a finite element model based on this microstructure was established to study the compressive behavior of the separator at the micro-scale. Additionally, a method was proposed to add fibrils into the image-based model to improve accuracy, which was validated using experimental data and scanning electron microscope images.

INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES (2022)

Add to Collection

Article Physics, Fluids & Plasmas

Improved recurrent generative model for reconstructing large-size porous media from two-dimensional images

Fan Zhang et al.

Summary: Modeling the three-dimensional structure from a 2D image is important for analyzing porous media properties. Deep learning-based methods show advantages in accuracy, diversity, and efficiency. However, current methods have limitations in reconstruction ability and information loss. This paper proposes an improved recurrent generative model to enhance reconstruction, with experimental results supporting its effectiveness.

PHYSICAL REVIEW E (2022)

Add to Collection

Article Physics, Fluids & Plasmas

Generative adversarial networks for reconstruction of three-dimensional porous media from two-dimensional slices

Denis Volkhonskiy et al.

Summary: In this paper, a deep learning architecture is proposed for the reconstruction of three-dimensional porous medium structures from two-dimensional slices. By fitting a distribution based on a given dataset, samples with similar properties are generated. Numerical experiments show that this method achieves good reconstruction results.

PHYSICAL REVIEW E (2022)

Add to Collection

Article Physics, Fluids & Plasmas

Deep-learning-based porous media microstructure quantitative characterization and reconstruction method

Yubo Huang et al.

Summary: Microstructure characterization and reconstruction plays a crucial role in uncovering the relationship between processing, structure, and properties of porous media behavior in computational materials science. However, existing methods struggle to achieve a balance between quantitative generation and characterization capability and reconstruction quality. This study presents an improved 3D Porous Media Microstructure generative adversarial network that enables high-quality microstructure generation with high controllability and accuracy. The proposed network demonstrates good adaptivity for microstructures with different random geometric configurations and can quantitatively control and predict complex microstructure features.

PHYSICAL REVIEW E (2022)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Reconstructing porous media using generative flow networks

Kelly M. Guan et al.

Summary: The use of deep learning methods to generate images of porous media allows for the rapid synthesis of realistic three-dimensional images with quantifiable topological features, matching measured trends in transport properties.

COMPUTERS & GEOSCIENCES (2021)

Add to Collection

Review Physics, Multidisciplinary

Reconstruction, optimization, and design of heterogeneous materials and media: Basic principles, computational algorithms, and applications

Muhammad Sahimi et al.

Summary: Modeling heterogeneous materials and media through reconstruction is crucial for a wide range of applications. The most fruitful approach involves developing models based on existing data to provide accurate predictions for properties without available data. Stochastic methods are preferred due to the large uncertainty in models and the inability of deterministic approaches to quantify uncertainty effectively.

PHYSICS REPORTS-REVIEW SECTION OF PHYSICS LETTERS (2021)

Add to Collection

Article Materials Science, Multidisciplinary

Stochastic 3D microstructure modeling of anodes in lithium-ion batteries with a particular focus on local heterogeneity

Benedikt Prifling et al.

Summary: The paper introduces a novel parametric stochastic 3D microstructure model based on random fields for optimizing electrode morphology and studying electrochemical properties. The microstructure-property relationships are derived and validated by combining virtual materials testing and computer simulations, with a specific focus on local heterogeneity of battery electrodes.

COMPUTATIONAL MATERIALS SCIENCE (2021)

Add to Collection

Review Chemistry, Physical

Guiding the Design of Heterogeneous Electrode Microstructures for Li-Ion Batteries: Microscopic Imaging, Predictive Modeling, and Machine Learning

Hongyi Xu et al.

Summary: The electrochemical and mechanical properties of lithium-ion battery materials heavily rely on their 3D microstructure characteristics. A quantitative understanding of the role played by stochastic microstructures is crucial for predicting material properties and guiding synthesis processes. Tailoring microstructure morphology is also a viable way to achieve optimal electrochemical and mechanical performance of lithium-ion cells. This review presents spatially and temporally resolved imaging of microstructure and electrochemical phenomena, microstructure statistical characterization and stochastic reconstruction, microstructure-resolved modeling for property prediction, and machine learning for microstructure design to facilitate the establishment of microstructure-resolved modeling and design methods. Perspectives on the unresolved challenges and opportunities in applying experimental data, modeling, and machine learning to improve understanding of materials and identify paths toward enhanced performance of lithium-ion cells are also discussed.

ADVANCED ENERGY MATERIALS (2021)

Add to Collection

Article Physics, Fluids & Plasmas

Three-dimensional reconstruction of porous media using super-dimension-based adjacent block-matching algorithm

Zhixin Xia et al.

Summary: The proposed method in this study improves accuracy and speed in reconstructing porous media by designing a special template for block matching and porosity control, achieving a 4-6 speedup factor compared to traditional SD methods.

PHYSICAL REVIEW E (2021)

Add to Collection

Review Nanoscience & Nanotechnology

A review on cathode materials for advanced lithium ion batteries: microstructure designs and performance regulations

Zhangxian Chen et al.

NANOTECHNOLOGY (2020)

Add to Collection

Article Multidisciplinary Sciences

3D microstructure design of lithium-ion battery electrodes assisted by X-ray nano-computed tomography and modelling

Xuekun Lu et al.

NATURE COMMUNICATIONS (2020)

Add to Collection

Article Computer Science, Hardware & Architecture

Generative Adversarial Networks

Ian Goodfellow et al.

COMMUNICATIONS OF THE ACM (2020)

Add to Collection

Article Energy & Fuels

RockFlow: Fast Generation of Synthetic Source Rock Images Using Generative Flow Models

Timothy I. Anderson et al.

ENERGIES (2020)

Add to Collection

Article Chemistry, Physical

Microstructure reconstruction of battery polymer separators by fusing 2D and 3D image data for transport property analysis

Hongyi Xu et al.

JOURNAL OF POWER SOURCES (2020)

Add to Collection

Article Physics, Fluids & Plasmas

Microstructure synthesis using style-based generative adversarial networks

Daria Fokina et al.

PHYSICAL REVIEW E (2020)

Add to Collection

Article Chemistry, Physical

High-throughput 3D reconstruction of stochastic heterogeneous microstructures in energy storage materials

Yanxiang Zhang et al.

NPJ COMPUTATIONAL MATERIALS (2019)

Add to Collection

Article Chemistry, Physical

Stochastic 3D microstructure reconstruction and mechanical modeling of anisotropic battery separators

Hongyi Xu et al.

JOURNAL OF POWER SOURCES (2019)

Add to Collection

Article Physics, Fluids & Plasmas

Dictionary optimization and constraint neighbor embedding-based dictionary mapping for superdimension reconstruction of porous media

Yang Li et al.

PHYSICAL REVIEW E (2019)

Add to Collection

Article Engineering, Electrical & Electronic

Generative Adversarial Networks An overview

Antonia Creswell et al.

IEEE SIGNAL PROCESSING MAGAZINE (2018)

Add to Collection

Article Physics, Fluids & Plasmas

Accurate modeling and evaluation of microstructures in complex materials

Pejman Tahmasebi

PHYSICAL REVIEW E (2018)

Add to Collection

Article Electrochemistry

Resolving the Discrepancy in Tortuosity Factor Estimation for Li-Ion Battery Electrodes through Micro-Macro Modeling and Experiment

Francois L. E. Usseglio-Viretta et al.

JOURNAL OF THE ELECTROCHEMICAL SOCIETY (2018)

Add to Collection

Article Physics, Fluids & Plasmas

Reconstruction of three-dimensional porous media using generative adversarial neural networks

Lukas Mosser et al.

PHYSICAL REVIEW E (2017)

Add to Collection

Article Materials Science, Multidisciplinary

Parametric stochastic 3D model for the microstructure of anodes in lithium-ion power cells

Daniel Westhoff et al.

COMPUTATIONAL MATERIALS SCIENCE (2017)

Add to Collection

Article Materials Science, Multidisciplinary

Stochastic 3D modeling of the microstructure of lithium-ion battery anodes via Gaussian random fields on the sphere

Julian Feinauer et al.

COMPUTATIONAL MATERIALS SCIENCE (2015)

Add to Collection

Article Engineering, Chemical

Quantitative relationships between microstructure and effective transport properties based on virtual materials testing

Gerd Gaiselmann et al.

AICHE JOURNAL (2014)

Add to Collection

Article Electrochemistry

Effects of three-dimensional cathode microstructure on the performance of lithium-ion battery cathodes

Andreas H. Wiedemann et al.

ELECTROCHIMICA ACTA (2013)

Add to Collection

Article Computer Science, Artificial Intelligence

3D Convolutional Neural Networks for Human Action Recognition

Shuiwang Ji et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2013)

Add to Collection

Review Materials Science, Multidisciplinary

Microstructural design considerations for Li-ion battery systems

Shen J. Dillon et al.

CURRENT OPINION IN SOLID STATE & MATERIALS SCIENCE (2012)

Add to Collection

Article Electrochemistry

Three-Dimensional Reconstruction of a LiCoO2 Li-Ion Battery Cathode

Tobias Hutzenlaub et al.

ELECTROCHEMICAL AND SOLID STATE LETTERS (2012)

Add to Collection

Article Multidisciplinary Sciences

A superior descriptor of random textures and its predictive capacity

Y. Jiao et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2009)

Add to Collection

Article Electrochemistry

Microstructural modeling and design of rechargeable lithium-ion batteries

RE Garcia et al.

JOURNAL OF THE ELECTROCHEMICAL SOCIETY (2005)

Add to Collection

Article Chemistry, Physical

Electrochemical performance of lithium ion battery, nano-silicon-based, disordered carbon composite anodes with different microstructures

XW Zhang et al.

JOURNAL OF POWER SOURCES (2004)

Add to Collection

Article Geosciences, Multidisciplinary

Spatial connectivity: From variograms to multiple-point measures

S Krishnan et al.

MATHEMATICAL GEOLOGY (2003)

Add to Collection

© Peeref 2019-2024. All rights reserved.