Search for: All records

Data-driven methods have attracted increasingly more attention in materials research since the advent of the material genome initiative. The combination of materials science with computer science, statistics, and data-driven methods aims to expediate materials research and applications and can utilize both new and archived research data. In this paper, we present a data driven and deep learning approach that builds a portion of the structure–property relationship for polymer nanocomposites. Analysis of archived experimental data motivates development of a computational model which allows demonstration of the approach and gives flexibility to sufficiently explore a wide range of structures. Taking advantage of microstructure reconstruction methods and finite element simulations, we first explore qualitative relationships between microstructure descriptors and mechanical properties, resulting in new findings regarding the interplay of interphase, volume fraction and dispersion. Then we present a novel deep learning approach that combines convolutional neural networks with multi-task learning for building quantitative correlations between microstructures and property values. The performance of the model is compared with other state-of-the-art strategies including two-point statistics and structure descriptor-based approaches. Lastly, the interpretation of the deep learning model is investigated to show that the model is able to capture physical understandings while learning. 

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. 

With an unprecedented combination of mechanical and electrical properties, polymer nanocomposites have the potential to be widely used across multiple industries. Tailoring nanocomposites to meet application specific requirements remains a challenging task, owing to the vast, mixed-variable design space that includes composition ( i.e. choice of polymer, nanoparticle, and surface modification) and microstructures ( i.e. dispersion and geometric arrangement of particles) of the nanocomposite material. Modeling properties of the interphase, the region surrounding a nanoparticle, introduces additional complexity to the design process and requires computationally expensive simulations. As a result, previous attempts at designing polymer nanocomposites have focused on finding the optimal microstructure for only a fixed combination of constituents. In this article, we propose a data centric design framework to concurrently identify optimal composition and microstructure using mixed-variable Bayesian optimization. This framework integrates experimental data with state-of-the-art techniques in interphase modeling, microstructure characterization and reconstructions and machine learning. Latent variable Gaussian processes (LVGPs) quantifies the lack-of-data uncertainty over the mixed-variable design space that consists of qualitative and quantitative material design variables. The design of electrically insulating nanocomposites is cast as a multicriteria optimization problem with the goal of maximizing dielectric breakdown strength while minimizing dielectric permittivity and dielectric loss. Within tens of simulations, our method identifies a diverse set of designs on the Pareto frontier indicating the tradeoff between dielectric properties. These findings project data centric design, effectively integrating experimental data with simulations for Bayesian Optimization, as an effective approach for design of engineered material systems.