Search for: All records

Data-driven materials design often encounters challenges where systems possess qualitative (categorical) information. Specifically, representing Metal-organic frameworks (MOFs) through different building blocks poses a challenge for designers to incorporate qualitative information into design optimization, and leads to a combinatorial challenge, with large number of MOFs that could be explored. In this work, we integrated Latent Variable Gaussian Process (LVGP) and Multi-Objective Batch-Bayesian Optimization (MOBBO) to identify top-performing MOFs adaptively, autonomously, and efficiently. We showcased that our method (i) requires no specific physical descriptors and only uses building blocks that construct the MOFs for global optimization through qualitative representations, (ii) is application and property independent, and (iii) provides an interpretable model of building blocks with physical justification. By searching only ~1% of the design space, LVGP-MOBBO identified all MOFs on the Pareto front and 97% of the 50 top-performing designs for the CO₂working capacity and CO₂/N₂selectivity properties.

 

Polymer nanodielectrics present a particularly challenging materials design problem for capacitive energy storage applications like polymer film capacitors. High permittivity and breakdown strength are needed to achieve high energy density and loss must be low. Strategies that increase permittivity tend to decrease the breakdown strength and increase loss. We hypothesize that a parameter space exists for fillers of modest aspect ratio functionalized with charge-trapping molecules that results in an increase in permittivity and breakdown strength simultaneously, while limiting increases in loss. In this work, we explore this parameter space, using physics-based, multiscale 3D dielectric property simulations, mixed-variable machine learning and Bayesian optimization to identify the compositions and morphologies which lead to the optimization of these competing properties. We employ first principle-based calculations for interface trap densities which are further used in breakdown strength calculations. For permittivity and loss calculations, we use continuum scale modelling and finite difference solution of Poisson’s equation for steady-state currents. We propose a design framework for optimizing multiple properties by tuning design variables including the microstructure and interface properties. Finally, we employ mixed-variable global sensitivity analysis to understand the complex interplay between four continuous microstructural and two categorical interface choices to extract further physical knowledge on the design of nanodielectrics.

 

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.