Yuksel C. Yabansu

Machine learning approaches for elastic localization linkages in high-contrast composite materials

There has been a growing recognition of the opportunities afforded by advanced data science and informatics approaches in addressing the computational demands of modeling and simulation of multiscale materials science phenomena. More specifically, the mining of microstructure–property relationships by various methods in machine learning and data mining opens exciting new opportunities that can potentially result in a fast and efficient material design. This work explores and presents multiple viable approaches for computationally efficient predictions of the microscale elastic strain fields in a three-dimensional (3-D) voxel-based microstructure volume element (MVE). Advanced concepts in machine learning and data mining, including feature extraction, feature ranking and selection, and regression modeling, are explored as data experiments. Improvements are demonstrated in a gradually escalated fashion achieved by (1) feature descriptors introduced to represent voxel neighborhood characteristics, (2) a reduced set of descriptors with top importance, and (3) an ensemble-based regression technique.

Context Aware Machine Learning Approaches for Modeling Elastic Localization in Three-Dimensional Composite Microstructures

The response of a composite material is the result of a complex interplay between the prevailing mechanics and the heterogenous structure at disparate spatial and temporal scales. Understanding and capturing the multiscale phenomena is critical for materials modeling and can be pursued both by physical simulation-based modeling as well as data-driven machine learning-based modeling. In this work, we build machine learning-based data models as surrogate models for approximating the microscale elastic response as a function of the material microstructure (also called the elastic localization linkage). In building these surrogate models, we particularly focus on understanding the role of contexts, as a link to the higher scale information that most evidently influences and determines the microscale response. As a result of context modeling, we find that machine learning systems with context awareness not only outperform previous best results, but also extend the parallelism of model training so as to maximize the computational efficiency.

Calibrated Localization Relationships for Polycrystalline Aggregates by Using Materials Knowledge System

Multiscale modeling of material systems demands novel solution strategies to simulating physical phenomena that occur in a hierarchy of length scales. Majority of the current approaches involve one way coupling such that the information is transferred from a lower length scale to a higher length scale. To enable bi-directional scale-bridging, a new data-driven framework called Materials Knowledge System (MKS) has been developed recently. The remarkable advantages of MKS in establishing computationally efficient localization linkages (e.g., spatial distribution of a field in lower length scale for an imposed loading condition in higher length scale) have been demonstrated in prior work. In these prior MKS studies, the effort was focused on composite materials that had a finite number of discrete local states. As a major extension, in this work, the MKS framework has been extended for polycrystalline aggregates which need to incorporate crystal lattice orientation as a continuous local state. This extension of the MKS framework for elastic deformation of polycrystals is achieved by employing compact Fourier representations of functions defined in the crystal orientation space. The viability of this new formulation will be presented for case studies involving single and multi-phase polycrystals.