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

Ruoqian Liu, Yuksel C. Yabansu, Ankit Agrawal*, Surya R. Kalidindi, Alok N. Choudhary

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

41 Scopus citations

Abstract

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.

Original languageEnglish (US)
Pages (from-to)192-208
Number of pages17
JournalIntegrating Materials and Manufacturing Innovation
Volume4
Issue number1
DOIs
StatePublished - Dec 1 2015

Keywords

  • Data mining
  • Elastic localization linkages
  • Ensemble-based regression
  • Materials informatics
  • Structure feature ranking
  • Structure feature selection

ASJC Scopus subject areas

  • Materials Science(all)
  • Industrial and Manufacturing Engineering

Fingerprint

Dive into the research topics of 'Machine learning approaches for elastic localization linkages in high-contrast composite materials'. Together they form a unique fingerprint.

Cite this