Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Multi deep learning-based stochastic microstructure reconstruction and high-fidelity micromechanics simulation of time-dependent ceramic matrix composite response

Journal Article · · Composite Structures
 [1];  [2]
  1. Arizona State University, Tempe, AZ (United States); Arizona State University
  2. Arizona State University, Tempe, AZ (United States)
+ Show Author Affiliations
A multi deep learning-based framework is developed for efficient, automated microstructure reconstruction and generation of stochastic representative volume elements (SRVEs) with periodic boundary conditions (PBCs) for accurate modeling of ceramic matrix composite (CMC) response. The methodology comprises a convolutional neural network coupled with regression layers to act as a vanilla regression network for semantic segmentation of the microstructure, allowing accurate characterization of the phases and their distributions at the microscale. Scanning electron microscope and confocal microscope are used to obtain C/SiNC and SiC/SiNC CMCs micrographs for vanilla regression testing. Microstructure variability in terms of fiber volume fraction and porosity are quantified through the output regression layer, ensuring accurate representation of material variability in SRVE construction. Generative adversarial network (GAN) and its variants are designed to produce high-fidelity SRVE, spanning CMCs microstructure variability space. A circular padding algorithm is developed to generate SRVEs with PBCs during training of GANs. The accuracy of the generated SRVEs is established through micromechanics simulations, where an efficient formulation of the high-fidelity generalized methods of cells (HFGMC) approach is used to compute the effective mechanical properties. Furthermore, an iterative algorithm is implemented in the HFGMC solver to simulate time-dependent deformation of SiC/SiNC subjected to creep loading conditions.
Research Organization:
Arizona State University, Tempe, AZ (United States)
Sponsoring Organization:
Army Research Office (ARO); National Energy Technology Laboratory (NETL); USDOE
Grant/Contract Number:
FE0031759
OSTI ID:
2396341
Alternate ID(s):
OSTI ID: 2396782
Report Number(s):
DOE--0031759
Journal Information:
Composite Structures, Journal Name: Composite Structures Vol. 345; ISSN 0263-8223
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (42)

Comparative Study of Convolution Neural Network’s Relu and Leaky-Relu Activation Functions book January 2019
Tensile creep behaviour of a silicon carbide-based fibre with a low oxygen content journal February 1995
Effects of Steam Environment on Fatigue Behavior of Two SiC/[SiC+Si3N4] Ceramic Composites at 1300°C journal September 2010
Automated segmentation of computed tomography images of fiber-reinforced composites by deep learning journal September 2020
Overview: Computer Vision and Machine Learning for Microstructural Characterization and Analysis journal September 2020
Microstructure Generation via Generative Adversarial Network for Heterogeneous, Topologically Complex 3D Materials journal December 2020
A micromechanics-based nonlocal constitutive equation and estimates of representative volume element size for elastic composites journal April 1996
Introduction book January 2013
Creep of SiC–SiC microcomposites journal October 1999
Analysis of oxidation-assisted stress-rupture of continuous fiber-reinforced ceramic matrix composites at intermediate temperatures journal April 1999
Microstructure reconstructions from 2-point statistics using phase-recovery algorithms journal March 2008
Modeling creep behavior in ceramic matrix composites journal May 2021
Improving direct physical properties prediction of heterogeneous materials from imaging data via convolutional neural network and a morphology-aware generative model journal July 2018
Uncorrelated volume element for stochastic modeling of microstructures based on local fiber volume fraction variation journal September 2015
Multiscale model of woven ceramic matrix composites considering manufacturing induced damage journal August 2015
Multiscale temperature-dependent ceramic matrix composite damage model with thermal residual stresses and manufacturing-induced damage journal July 2021
Woven ceramic matrix composite surrogate model based on physics-informed recurrent neural network journal February 2023
Tensile creep behavior of SiCf/SiC ceramic matrix minicomposites journal December 2020
Creep behavior and failure mechanisms of CVI and PIP SiC/SiC composites at temperatures to 1650 °C in air journal October 2021
Modeling the two-way coupling of stress, diffusion, and oxidation in heterogeneous CMC microstructures journal February 2023
In-plane thermal expansion behavior of M55J carbon fiber reinforced SiC matrix composite journal January 2024
Mesoscale characterization of local property distributions in heterogeneous electrodes journal May 2018
Computational microstructure characterization and reconstruction: Review of the state-of-the-art techniques journal June 2018
The Many Faces of Mixed Ion Perovskites: Unraveling and Understanding the Crystallization Process journal November 2017
Pores for thought: generative adversarial networks for stochastic reconstruction of 3D multi-phase electrode microstructures with periodic boundaries journal June 2020
Super-resolving material microstructure image via deep learning for microstructure characterization and mechanical behavior analysis journal June 2021
Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion journal April 2021
Efficient Multiscale Modeling Framework for Triaxially Braided Composites using Generalized Method of Cells journal April 2011
Review: creep of fibre-reinforced ceramic matrix composites journal February 2019
The influence of the representative volume element (RVE) size on the homogenized response of cured fiber composites journal September 2012
A theory of the yielding and plastic flow of anisotropic metals journal May 1948
Microstructural degeneracy associated with a two-point correlation function and its information content journal May 2012
ImageNet: A large-scale hierarchical image database
  • Deng, Jia; Dong, Wei; Socher, Richard
  • 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), 2009 IEEE Conference on Computer Vision and Pattern Recognition https://doi.org/10.1109/CVPR.2009.5206848
conference June 2009
Rethinking the Inception Architecture for Computer Vision conference June 2016
Tensile Creep Behavior of SiC-Based Fibers With a Low Oxygen Content journal April 2007
Oxidation Kinetics and Stress Effects for the Oxidation of Continuous Carbon Fibers within a Microcracked C/SiC Ceramic Matrix Composite journal February 2008
Modeling environmentally induced property degradation of SiC/BN/SiC ceramic matrix composites journal December 2017
Microstructural Materials Design Via Deep Adversarial Learning Methodology journal October 2018
A Deep Adversarial Learning Methodology for Designing Microstructural Material Systems
  • Li, Xiaolin; Yang, Zijiang; Brinson, L. Catherine
  • ASME 2018 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Volume 2B: 44th Design Automation Conference https://doi.org/10.1115/DETC2018-85633
conference November 2018
Generative adversarial networks journal October 2020
Multiscale characterization and representation of variability in ceramic matrix composites journal January 2021
High-fidelity micromechanical modeling of the effects of defects on damage and creep behavior in single tow ceramic matrix composite journal December 2022

Figures / Tables (18)

Fig. 1(p. 4)figure Fig. 1
Fig. 2(p. 7)figure Fig. 2
Fig. 3(p. 8)figure Fig. 3
Fig. 4(p. 11)figure Fig. 4
Fig. 5(p. 12)figure Fig. 5
Fig. 6(p. 13)figure Fig. 6
Fig. 7(p. 15)figure Fig. 7
Fig. 8(p. 16)figure Fig. 8
Fig. 9(p. 17)figure Fig. 9
Fig. 10(p. 18)figure Fig. 10
Fig. 11(p. 19)figure Fig. 11
Table 1(p. 23)table Table 1
Table 2(p. 23)table Table 2
Fig. 12(p. 24)figure Fig. 12
Fig. 13(p. 24)figure Fig. 13
Table 3(p. 25)table Table 3
Fig. 14(p. 26)figure Fig. 14
Fig. 15(p. 27)figure Fig. 15

Similar Records

Related Subjects

36 MATERIALS SCIENCE
Ceramic matrix composites
Creep
Deep learning regression
Generative adversarial networks
Micromechanics homogenization