Physics-Informed Machine Learning Model for Ceramic Matrix Composite Creep

Hamza, Mohamed; Borkowski, Luke; Chattopadhyay, Aditi

doi:10.2514/6.2025-2516

Physics-Informed Machine Learning Model for Ceramic Matrix Composite Creep

Conference · Fri Jan 03 04:00:00 EST 2025 · AIAA SCITECH 2025 Forum

DOI:https://doi.org/10.2514/6.2025-2516· OSTI ID:2515638

Hamza, Mohamed ^[1]; Borkowski, Luke ^[2]; Chattopadhyay, Aditi ^[3]

Arizona State University, Tempe, AZ (United States); Arizona State University
RTX Technology Research Center, East Hartford, CT (United States)
Arizona State University, Tempe, AZ (United States)

A physics-informed recurrent neural network (RNN) based surrogate model is developed to emulate the nonlinear, time-dependent constitutive behavior of ceramic matrix composites (CMCs) driven by matrix damage and constituent creep at the microscale. Physics-informed constraints are introduced into the surrogate model through regularization to ground the prediction in physics and improve its predictive capabilities. Training data is generated using the high-fidelity generalized method of cells (HFGMC) approach which calls appropriate creep and damage models for each of the constituents. This coupling permits simulating the nonlinear behavior of CMCs based on constituent response at the microscale along with microstructural features such as fiber and porosity volume fraction and fiber radius. The microscale repeating unit cell is loaded under creep fatigue conditions to replicate the material loading experienced in a turbine engine. Therefore, the RNN-based surrogate model is tasked with predicting, as a function of variable input stress sequence, temperature, and microstructural features, the resulting strain history response while satisfying physical constraints related to creep rate, isochoric inelastic deformation, and strain energy density. The trained surrogate model is shown to effectively match the strain history over quantified distributions of microstructural features and relevant loading regimes and temperatures. Neural network based surrogate models can offer efficient alternatives to running computationally intensive multiscale material models to simulate the nonlinear response of large structural models. Therefore, the presented work provides evidence towards the feasibility of developing, training, and running such models for CMCs with complex microstructures, nonlinear time-dependent material response, and under non-monotonic loading conditions.

View Conference

Research Organization:: Arizona State University, Tempe, AZ (United States)

Sponsoring Organization:: USDOE; Army Research Office (ARO)

DOE Contract Number:: FE0031759

OSTI ID:: 2515638

Report Number(s):: DOE--0031759

Conference Information:: Journal Name: AIAA SCITECH 2025 Forum

Country of Publication:: United States

Language:: English

References (28)

Woven ceramic matrix composite surrogate model based on physics-informed recurrent neural network Borkowski, L.; Skinner, T.; Chattopadhyay, A. Composite Structures, Vol. 305 https://doi.org/10.1016/j.compstruct.2022.116455	journal	February 2023
Recurrent neural network-based multiaxial plasticity model with regularization for physics-informed constraints Borkowski, L.; Sorini, C.; Chattopadhyay, A. Computers & Structures, Vol. 258 https://doi.org/10.1016/j.compstruc.2021.106678	journal	January 2022
Solving unsymmetric sparse systems of linear equations with PARDISO Schenk, Olaf; Gärtner, Klaus Future Generation Computer Systems, Vol. 20, Issue 3 https://doi.org/10.1016/j.future.2003.07.011	journal	April 2004
Predicting the mechanical response of oligocrystals with deep learning Frankel, A. L.; Jones, R. E.; Alleman, C. Computational Materials Science, Vol. 169 https://doi.org/10.1016/j.commatsci.2019.109099	journal	November 2019
Deep learning predicts path-dependent plasticity Mozaffar, M.; Bostanabad, R.; Chen, W. Proceedings of the National Academy of Sciences, Vol. 116, Issue 52 https://doi.org/10.1073/pnas.1911815116	journal	December 2019
Multiscale ceramic matrix composite thermomechanical damage model with fracture mechanics and internal state variables Skinner, Travis; Rai, Ashwin; Chattopadhyay, Aditi Composite Structures, Vol. 236 https://doi.org/10.1016/j.compstruct.2019.111847	journal	March 2020
Formulation of the high-fidelity generalized method of cells with arbitrary cell geometry for refined micromechanics and damage in composites Haj-Ali, Rami; Aboudi, Jacob International Journal of Solids and Structures, Vol. 47, Issue 25-26 https://doi.org/10.1016/j.ijsolstr.2010.08.022	journal	December 2010
Application of artificial neural networks in micromechanics for polycrystalline metals Ali, Usman; Muhammad, Waqas; Brahme, Abhijit International Journal of Plasticity, Vol. 120 https://doi.org/10.1016/j.ijplas.2019.05.001	journal	September 2019
Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network Ghavamian, F.; Simone, A. Computer Methods in Applied Mechanics and Engineering, Vol. 357 https://doi.org/10.1016/j.cma.2019.112594	journal	December 2019
Computational microstructure characterization and reconstruction: Review of the state-of-the-art techniques Bostanabad, Ramin; Zhang, Yichi; Li, Xiaolin Progress in Materials Science, Vol. 95 https://doi.org/10.1016/j.pmatsci.2018.01.005	journal	June 2018
The Sol Supercomputer at Arizona State University Jennewein, Douglas M.; Lee, Johnathan; Kurtz, Chris Practice and Experience in Advanced Research Computing https://doi.org/10.1145/3569951.3597573	conference	July 2023
Overview: Computer Vision and Machine Learning for Microstructural Characterization and Analysis Holm, Elizabeth A.; Cohn, Ryan; Gao, Nan Metallurgical and Materials Transactions A, Vol. 51, Issue 12 https://doi.org/10.1007/s11661-020-06008-4	journal	September 2020
Multiscale characterization and representation of variability in ceramic matrix composites Khafagy, Khaled H.; Datta, Siddhant; Chattopadhyay, Aditi Journal of Composite Materials https://doi.org/10.1177/0021998320978445	journal	January 2021
Physics-based recurrent neural network model for flight path trajectory prediction under high-altitude stall Hamza, Mohamed; Mutnur, Venkatasatyanand; Kim, Hwa-Young AIAA SCITECH 2023 Forum https://doi.org/10.2514/6.2023-0147	conference	January 2023
Modeling creep behavior in ceramic matrix composites Khafagy, Khaled H.; Sorini, Christopher; Skinner, Travis Ceramics International, Vol. 47, Issue 9 https://doi.org/10.1016/j.ceramint.2021.01.125	journal	May 2021
Multiscale computation on feedforward neural network and recurrent neural network Li, Bin; Zhuang, Xiaoying Frontiers of Structural and Civil Engineering, Vol. 14, Issue 6 https://doi.org/10.1007/s11709-020-0691-7	journal	December 2020
Multi deep learning-based stochastic microstructure reconstruction and high-fidelity micromechanics simulation of time-dependent ceramic matrix composite response Hamza, Mohamed H.; Chattopadhyay, A. Composite Structures, Vol. 345 https://doi.org/10.1016/j.compstruct.2024.118360	journal	October 2024
Multiscale model of woven ceramic matrix composites considering manufacturing induced damage Borkowski, Luke; Chattopadhyay, Aditi Composite Structures, Vol. 126 https://doi.org/10.1016/j.compstruct.2015.02.015	journal	August 2015
On the potential of recurrent neural networks for modeling path dependent plasticity Gorji, Maysam B.; Mozaffar, Mojtaba; Heidenreich, Julian N. Journal of the Mechanics and Physics of Solids, Vol. 143 https://doi.org/10.1016/j.jmps.2020.103972	journal	October 2020
Impact of Buckypaper on the Mechanical Properties and Failure Modes of Composites Tripathi, Kartik; Hamza, Mohamed H.; Chattopadhyay, Aditi American Society for Composites 2023 https://doi.org/10.12783/asc38/36707	conference	September 2023
Using neural networks to represent von Mises plasticity with isotropic hardening Zhang, Annan; Mohr, Dirk International Journal of Plasticity, Vol. 132 https://doi.org/10.1016/j.ijplas.2020.102732	journal	September 2020
A recurrent neural network-accelerated multi-scale model for elasto-plastic heterogeneous materials subjected to random cyclic and non-proportional loading paths Wu, Ling; Nguyen, Van Dung; Kilingar, Nanda Gopala Computer Methods in Applied Mechanics and Engineering, Vol. 369 https://doi.org/10.1016/j.cma.2020.113234	journal	September 2020
Multiscale temperature-dependent ceramic matrix composite damage model with thermal residual stresses and manufacturing-induced damage Skinner, Travis; Chattopadhyay, Aditi Composite Structures, Vol. 268 https://doi.org/10.1016/j.compstruct.2021.114006	journal	July 2021
A neural network enhanced system for learning nonlinear constitutive law and failure initiation criterion of composites using indirectly measurable data Liu, Xin; Tao, Fei; Yu, Wenbin Composite Structures, Vol. 252 https://doi.org/10.1016/j.compstruct.2020.112658	journal	November 2020
Artificial Neural Networks in numerical modelling of composites Lefik, M.; Boso, D. P.; Schrefler, B. A. Computer Methods in Applied Mechanics and Engineering, Vol. 198, Issue 21-26 https://doi.org/10.1016/j.cma.2008.12.036	journal	May 2009
Learning constitutive relations using symmetric positive definite neural networks Xu, Kailai; Huang, Daniel Z.; Darve, Eric Journal of Computational Physics, Vol. 428 https://doi.org/10.1016/j.jcp.2020.110072	journal	March 2021
Self-consistent clustering analysis: An efficient multi-scale scheme for inelastic heterogeneous materials Liu, Zeliang; Bessa, M. A.; Liu, Wing Kam Computer Methods in Applied Mechanics and Engineering, Vol. 306 https://doi.org/10.1016/j.cma.2016.04.004	journal	July 2016
An efficient implementation of the high-fidelity generalized method of cells for complex microstructures Balusu, Kranthi; Skinner, Travis; Chattopadhyay, Aditi Computational Materials Science, Vol. 186 https://doi.org/10.1016/j.commatsci.2020.110004	journal	January 2021

Similar Records

Woven ceramic matrix composite surrogate model based on physics-informed recurrent neural network

Journal Article · Mon Nov 07 19:00:00 EST 2022 · Composite Structures · OSTI ID:2394692

Recurrent neural network-based multiaxial plasticity model with regularization for physics-informed constraints

Journal Article · Sun Sep 26 20:00:00 EDT 2021 · Computers and Structures · OSTI ID:1977023

Related Subjects

ceramic matrix composites
creep
damage
physics-based micromechanics model
recurrent neural network
surrogate model

Physics-Informed Machine Learning Model for Ceramic Matrix Composite Creep

Citation Formats

References (28)

Similar Records

Related Subjects