Gaussian-Process-Driven Adaptive Sampling for Reduced-Order Modeling of Texture Effects in Polycrystalline Alpha-Ti

Tallman, Aaron E.; Stopka, Krzysztof S.; Swiler, Laura Painton; Wang, Yan; Kalidindi, Surya R.

doi:10.1007/s11837-019-03553-1

Cited by 21 publications

(12 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although many surrogate model building approaches can be used for building structureproperty linkages, prior work has shown the benefits of using Gaussian process regression (GPR) in combination with the MKS feature engineering described earlier [8,9,[15][16][17][18][19][20]. GPR is particularly powerful when building surrogate models for complex nonlinear systems/phenomena, where the parametric model forms are not yet established.…”

Section: Gaussian Process Regression Modelsmentioning

confidence: 99%

“…The feature engineering developed in the MKS framework is unsupervised in that the microstructure feature selection is completely uninfluenced by the output variables targeted by the surrogate model. Although a large number of options exist for building the surrogate models of interest, recent work in the MKS framework [8,9,[15][16][17][18][19][20] has demonstrated that Gaussian process regression (GPR) [14,21] offers advantages because of its ability to formulate non-parametric models while allowing for a rigorous consideration of the prediction uncertainty.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Feature engineering for microstructure-property mapping in organic photovoltaics

Hashemi¹,

Baskar²,

Casey³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Linking the highly complex morphology of organic photovoltaic (OPV) thin films to their charge transport properties is critical for achieving high performance material system that serves as a cost-efficient approach for energy harvesting. In this paper, a novel unsupervised feature engineering framework is developed and used to establish reduced-order structure-property linkages for OPV films. This framework takes advantage of digital image processing algorithms to identify the salient material features of OPVs undergoing the charge transport phenomenon. These material states are then used to obtain a low-dimensional representation of OPV microstructures via 2-point spatial correlations and principal component analysis. It is found that in addition to the material PC scores, two distance-based metrics are required to complete the microstructure quantification of complex OPVs. A localized version of the Gaussian process (laGP) is then used to link the material PC scores as well as the two distance-based metrics to the short-circuit current of OPVs. It is demonstrated that the unsupervised feature engineering framework presented in this paper in conjunction with the laGP can lead to high-fidelity and accurate data-driven structure-property linkages for OPV films.

show abstract

Section: Gaussian Process Regression Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Feature engineering for microstructure-property mapping in organic photovoltaics

Hashemi¹,

Baskar²,

Casey³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Fernadez et al Fernandez-Zelaia et al (2018) utilized Bayesian inference to quantify the uncertainty in stressstrain curves, where model parameters are treated as random variables. Tallman et al Tallman et al (2019Tallman et al ( , 2020 applied Gaussian process regression and the Materials Knowledge System framework to predict a set of homogenized materials properties with uncertainty from a distribution function for crystallography orientations and textures. Inductive design exploration method (IDEM) Ellis and McDowell (2017);McDowell et al (2009); Choi et al (2008) has been introduced as a materials design methodology to identify feasible and robust design for microstructure features, which has been broadly applied to many practical problems.…”

Section: Introductionmentioning

confidence: 99%

Microstructure-sensitive uncertainty quantification for crystal plasticity finite element constitutive models using stochastic collocation methods

Tran¹,

Wildey²,

Lim³

2022

Preprint

View full text Add to dashboard Cite

Uncertainty quantification (UQ) plays a major role in verification and validation for computational engineering models and simulations, and establishes trust in the predictive capability of computational models. In the materials science and engineering context, where the process-structure-property-performance linkage is well known to be the only road mapping from manufacturing to engineering performance, numerous integrated computational materials engineering (ICME) models have been developed across a wide spectrum of length-scales and time-scales to relieve the burden of resource-intensive experiments. Within the structure-property linkage, crystal plasticity finite element method (CPFEM) models have been widely used since they are one of a few ICME toolboxes that allows numerical predictions, providing the bridge from microstructure to materials properties and performances. Several constitutive models have been proposed in the last few decades to capture the mechanics and plasticity behavior of materials. While some UQ studies have been performed, the robustness and uncertainty of these constitutive models have not been rigorously established. In this work, we apply a stochastic collocation (SC) method, which is mathematically rigorous and has been widely used in the field of UQ, to quantify the uncertainty of three most commonly used constitutive models in CPFEM, namely phenomenological models (with and without twinning), and dislocationdensity-based constitutive models, for three different types of crystal structures, namely face-centered cubic (fcc) copper (Cu), body-centered cubic (bcc) tungsten (W), and hexagonal close packing (hcp) magnesium (Mg). Our numerical results not only quantify the uncertainty of these constitutive models in stress-strain curve, but also analyze the global sensitivity of the underlying constitutive parameters with respect to the initial yield behavior, which may be helpful for robust constitutive model calibration works in the future.

show abstract

“…Diehl et al [14] proposed an ICME workflow coupling DAMASK and DREAM.3D, which we also adopt in this work, that was subsequently employed in Liu et al [31,30] and Diehl et al [15] to quantify the influence of grain shape and crystallographic orientation of fine-structure dual-phase and high-strength low-alloy steel respectively. A Gaussian process (GP) regression model and a Materials Knowledge System framework were combined in Tallman et al [48,49] to model a set of homogenized materials properties with respect to an orientation distribution function. Liu et al [28,29] developed a physics-based microstructure descriptors approach to parameterize microstructures as inputs and constructed the structure-properties map for a localization problem using regression trees and support vector machines.…”

Section: Introductionmentioning

confidence: 99%

“…This surrogate model can then be exhaustively sampled without running ICME models which greatly reduces the computational efforts. While any ML tools can be used for this surrogate, in this paper, we limit the scope of our study to the well-known Gaussian process (GP) regression model, as demonstrated by Tallman et al [48,49]. For each realization of this vector, an ensemble of microstructure SVEs is generated using DREAM.3D, and the homogeneized material respose is calculated using a CPFEM model, e.g., DAMASK.…”

Section: Introductionmentioning

confidence: 99%

Solving stochastic inverse problems for property-structure linkages using data-consistent inversion and machine learning

Tran¹,

Wildey²

2020

Preprint

View full text Add to dashboard Cite

Determining process-structure-property linkages is one of the key objectives in material science, and uncertainty quantification plays a critical role in understanding both process-structure and structure-property linkages. In this work, we seek to learn a distribution of microstructure parameters that are consistent in the sense that the forward propagation of this distribution through a crystal plasticity finite element model (CPFEM) matches a target distribution on materials properties. This stochastic inversion formulation infers a distribution of acceptable/consistent microstructures, as opposed to a deterministic solution, which expands the range of feasible designs in a probabilistic manner. To solve this stochastic inverse problem, we employ a recently developed uncertainty quantification (UQ) framework based on push-forward probability measures, which combines techniques from measure theory and Bayes' rule to define a unique and numerically stable solution. This approach requires making an initial prediction using an initial guess for the distribution on model inputs and solving a stochastic forward problem. To reduce the computational burden in solving both stochastic forward and stochastic inverse problems, we combine this approach with a machine learning (ML) Bayesian regression model based on Gaussian processes and demonstrate the proposed methodology on two representative case studies in structure-property linkages.Keywords structure-property ¨crystal plasticity ¨Gaussian process ¨ICME ¨machine learning data-consistent inversion ¨uncertainty quantification ¨materials design

show abstract

Gaussian-Process-Driven Adaptive Sampling for Reduced-Order Modeling of Texture Effects in Polycrystalline Alpha-Ti

Cited by 21 publications

References 12 publications

Feature engineering for microstructure-property mapping in organic photovoltaics

Feature engineering for microstructure-property mapping in organic photovoltaics

Microstructure-sensitive uncertainty quantification for crystal plasticity finite element constitutive models using stochastic collocation methods

Solving stochastic inverse problems for property-structure linkages using data-consistent inversion and machine learning

Contact Info

Product

Resources

About