Mining structure-property relationships in polymer nanocomposites using data driven finite element analysis and multi-task convolutional neural networks

Yixing Wang, Min Zhang, Anqi Lin, Akshay Iyer, Aditya Shanker Prasad, Xiaolin Li, Yichi Zhang, Linda S. Schadler, Wei Chen, L. Catherine Brinson*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

Abstract

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.

Original languageEnglish (US)
Pages (from-to)962-975
Number of pages14
JournalMolecular Systems Design and Engineering
Volume5
Issue number5
DOIs
StatePublished - Jun 1 2020

ASJC Scopus subject areas

  • Chemistry (miscellaneous)
  • Chemical Engineering (miscellaneous)
  • Biomedical Engineering
  • Energy Engineering and Power Technology
  • Process Chemistry and Technology
  • Industrial and Manufacturing Engineering
  • Materials Chemistry

Fingerprint

Dive into the research topics of 'Mining structure-property relationships in polymer nanocomposites using data driven finite element analysis and multi-task convolutional neural networks'. Together they form a unique fingerprint.

Cite this