More Like this

1. Graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials

   https://doi.org/10.1038/s41524-021-00574-w  

   Dai, Minyi ; Demirel, Mehmet F. ; Liang, Yingyu ; Hu, Jia-Mian ( July 2021 , npj Computational Materials)

   Various machine learning models have been used to predict the properties of polycrystalline materials, but none of them directly consider the physical interactions among neighboring grains despite such microscopic interactions critically determining macroscopic material properties. Here, we develop a graph neural network (GNN) model for obtaining an embedding of polycrystalline microstructure which incorporates not only the physical features of individual grains but also their interactions. The embedding is then linked to the target property using a feed-forward neural network. Using the magnetostriction of polycrystalline Tb_0.3Dy_0.7Fe₂alloys as an example, we show that a single GNN model with fixed network architecture and hyperparameters allows for a low prediction error of ~10% over a group of remarkably different microstructures as well as quantifying the importance of each feature in each grain of a microstructure to its magnetostriction. Such a microstructure-graph-based GNN model, therefore, enables an accurate and interpretable prediction of the properties of polycrystalline materials.

    

   more » « less
2. Designing Ti-6Al-4V microstructure for strain delocalization using neural networks

   https://doi.org/10.1186/s41313-024-00055-9  

   Ahmadikia, Behnam ; Beyerlein, Adolph L ; Hestroffer, Jonathan M ; Kumar, M Arul ; Beyerlein, Irene J ( December 2024 , Journal of Materials Science: Materials Theory)

   The deformation behavior of Ti-6Al-4V titanium alloy is significantly influenced by slip localized within crystallographic slip bands. Experimental observations reveal that intense slip bands in Ti-6Al-4V form at strains well below the macroscopic yield strain and may serially propagate across grain boundaries, resulting in long-range localization that percolates through the microstructure. These connected, localized slip bands serve as potential sites for crack initiation. Although slip localization in Ti-6Al-4V is known to be influenced by various factors, an investigation of optimal microstructures that limit localization remains lacking. In this work, we develop a novel strategy that integrates an explicit slip band crystal plasticity technique, graph networks, and neural network models to identify Ti-6Al-4V microstructures that reduce the propensity for strain localization. Simulations are conducted on a dataset of 3D polycrystals, each represented as a graph to account for grain neighborhood and connectivity. The results are then used to train neural network surrogate models that accurately predict localization-based properties of a polycrystal, given its microstructure. These properties include the ratio of slip accumulated in the band to that in the matrix, fraction of total applied strain accommodated by slip bands, and spatial connectivity of slip bands throughout the microstructure. The initial dataset is enriched by synthetic data generated by the surrogate models, and a grid search optimization is subsequently performed to find optimal microstructures. Describing a 3D polycrystal with only a few features and a combination of graph and neural network models offer robustness compared to the alternative approaches without compromising accuracy. We show that while each material property is optimized through a unique microstructure solution, elongated grain shape emerges as a recurring feature among all optimal microstructures. This finding suggests that designing microstructures with elongated grains could potentially mitigate strain localization without compromising strength.

    

   more » « less
3. Materials Informatics and Data System for Polymer Nanocomposites Analysis and Design

   https://doi.org/10.1142/9789811204555_0003  

   Chen, Wei ; Schadler, Linda ; Brinson, Cate ; Wang, Yixing ; Zhang, Yichi ; Prasad, Aditya ; Li, Xiaolin ; Iyer, Akshay ( October 2019 , Handbook on Big Data and Machine Learning in the Physical Sciences)

   The application of Materials Informatics to polymer nanocomposites would result in faster development and commercial implementation of these promising materials, particularly in applications requiring a unique combination of properties. This chapter focuses on a new data resource for nanocomposites — NanoMine — and the tools, models, and algorithms that support data-driven materials design. The chapter begins with a brief introduction to NanoMine, including the data structure and tools available. Critical to the ability to design nanocomposites, however, is developing robust structure–property–processing (s–p–p) relationships. Central to this development is the choice of appropriate microstructure characterization and reconstruction (MCR) techniques that capture a complex morphology and ultimately build statistically equivalent reconstructed composites for accurate modeling of properties. A wide range of MCR techniques is reviewed followed by an introduction of feature selection and feature extraction techniques to identify the most significant microstructure features for dimension reduction. This is then followed by examples of using a descriptor-based representation to create processing–structure (p–s) and structure–property (s–p) relationships for use in design. To overcome the difficulty in modeling the interphase region surrounding nanofillers, an adaptive sampling approach is presented to inversely determine the inter-phase properties based on both FEM simulations and physical experiment data of bulk properties. Finally, a case study for nanodielectrics in a capacitor is introduced to demonstrate the integration of the p–s and s–p relationships to develop optimized materials for achieving multiple desired properties. 

   more » « less
4. Evolutive screening of candidates for new materials using genetic algorithms and deep learning

   https://doi.org/10.18687/LACCEI2023.1.1.651  

   Tatis_Posada, David ; Ramos_Álamo, María ; Sierra, Heidy ; Arzuaga, Emmanuel ( January 2023 , Proceedings of the LACCEI international multiconference for engineering education and technology)

   ifferent mechanisms are used for the discovery of materials. These include creating a material by trial-and-error process without knowing its properties. Other methods are based on computational simulations or mathematical and statistical approaches, such as Density Functional Theory (DFT). A well-known strategy combines elements to predict their properties and selects a set of those with the properties of interest. Carrying out exhaustive calculations to predict the properties of these found compounds may require a high computational cost. Therefore, there is a need to create methods for identifying materials with a desired set of properties while reducing the search space and, consequently, the computational cost. In this work, we present a genetic algorithm that can find a higher percentage of compounds with specific properties than state-of-the-art methods, such as those based on combinatorial screening. Both methods are compared in the search for ternary compounds in an unconstrained space, using a Deep Neural Network (DNN) to predict properties such as formation enthalpy, band gap, and stability; we will focus on formation enthalpy. As a result, we provide a genetic algorithm capable of finding up to 60% more compounds with atypical values of properties, using DNNs for their prediction. 

   more » « less
5. METASET: Exploring Shape and Property Spaces for Data-Driven Metamaterials Design

   https://doi.org/10.1115/1.4048629  

   Chan, Yu-Chin ; Ahmed, Faez ; Wang, Liwei ; Chen, Wei ( March 2021 , Journal of Mechanical Design)

   null (Ed.)

   Abstract Data-driven design of mechanical metamaterials is an increasingly popular method to combat costly physical simulations and immense, often intractable, geometrical design spaces. Using a precomputed dataset of unit cells, a multiscale structure can be quickly filled via combinatorial search algorithms, and machine learning models can be trained to accelerate the process. However, the dependence on data induces a unique challenge: an imbalanced dataset containing more of certain shapes or physical properties can be detrimental to the efficacy of data-driven approaches. In answer, we posit that a smaller yet diverse set of unit cells leads to scalable search and unbiased learning. To select such subsets, we propose METASET, a methodology that (1) uses similarity metrics and positive semi-definite kernels to jointly measure the closeness of unit cells in both shape and property spaces and (2) incorporates Determinantal Point Processes for efficient subset selection. Moreover, METASET allows the trade-off between shape and property diversity so that subsets can be tuned for various applications. Through the design of 2D metamaterials with target displacement profiles, we demonstrate that smaller, diverse subsets can indeed improve the search process as well as structural performance. By eliminating inherent overlaps in a dataset of 3D unit cells created with symmetry rules, we also illustrate that our flexible method can distill unique subsets regardless of the metric employed. Our diverse subsets are provided publicly for use by any designer. 

   more » « less