CNN-based prediction of microstructure-derived random property fields of composite materials

DOI10.1016/J.CMA.2024.117207MaRDI QIDQ6595874zbMATH OpenFDO

Authors Panagiotis Gavallas, George Stefanou, Dimitrios Savvas, Cécile Mattrand, Jean-Marc Bourinet

Publication date 30 August 2024

Published in Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.CMA.2024.117207

zbMATH Keywords

CNNcomposite materialmechanical propertiesrandom fields

Mathematics Subject Classification ID

Random materials and composite materials (74A40) Micromechanics of solids (74M25) Numerical and other methods in solid mechanics (74S99)

Recommendations

• A three-dimensional prediction method of stiffness properties of composites based on deep learning
• Deep CNNs as universal predictors of elasticity tensors in homogenization
• Three-dimensional microstructure generation using generative adversarial neural networks in the context of continuum micromechanics
• Predicting the effective mechanical property of heterogeneous materials by image based modeling and deep learning
• Ensemble wavelet-learning approach for predicting the effective mechanical properties of concrete composite materials

Cites work

• A computational approach to handle complex microstructure geometries.
• A finite element method for crack growth without remeshing
• A neural network-aided Bayesian identification framework for multiscale modeling of nanocomposites
• Bayesian identification and model comparison for random property fields derived from material microstructure
• Computational micro-to-macro transitions of discretized microstructures undergoing small strains
• Deep CNNs as universal predictors of elasticity tensors in homogenization
• Deep learning
• Determination of RVE size for random composites with local volume fraction variation
• Probabilistic models for stochastic elliptic partial differential equations
• Stochastic finite element analysis of composite structures based on mesoscale random fields of material properties
• Stochastic modelling of symmetric positive definite material tensors
• The stochastic finite element method: past, present and future
• Theoretical framework and experimental procedure for modelling mesoscopic volume fraction stochastic fluctuations in fiber reinforced composites
• Three-dimensional microstructure generation using generative adversarial neural networks in the context of continuum micromechanics

Cited in

(3)

• Deep CNNs as universal predictors of elasticity tensors in homogenization
• A review of recent advances in surrogate models for uncertainty quantification of high-dimensional engineering applications
• Vision transformers for modeling of nonlinear heterogeneous materials

This page was built for publication: CNN-based prediction of microstructure-derived random property fields of composite materials

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6595874)