A machine learning-based design representation method for designing heterogeneous microstructures

Hongyi Xu, Ruoqian Liu, Alok Nidhi Choudhary, Wei Chen*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

In designing microstructural materials systems, one of the key research questions is how to represent the microstructural design space quantitatively using a descriptor set that is sufficient yet small enough to be tractable. Existing approaches describe complex microstructures either using a small set of descriptors that lack sufficient level of details, or using generic high order microstructure functions of infinite dimensionality without explicit physical meanings. We propose a new machine learning-based method for identifying the key microstructure descriptors from vast candidates as potential microstructural design variables. With a large number of candidate microstructure descriptors collected from literature covering a wide range of microstructural material systems a 4-step machine learning-based method is developed to eliminate redundant microstructure descriptors via image analyses, to identify key microstructure descriptors based on structureproperty data, and to determine the microstructure design variables. The training criteria of the supervised learning process include both microstructure correlation functions and material properties. The proposed methodology effectively reduces the infinite dimension of the microstructure design space to a small set of descriptors without a significant information loss. The benefits are demonstrated by an example of polymer nanocomposites optimization. We compare designs using key microstructure descriptors versus using empiricallychosen microstructure descriptors to validate the proposed method.

Original languageEnglish (US)
Title of host publication40th Design Automation Conference
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791846322
DOIs
StatePublished - Jan 1 2014
EventASME 2014 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2014 - Buffalo, United States
Duration: Aug 17 2014Aug 20 2014

Publication series

NameProceedings of the ASME Design Engineering Technical Conference
Volume2B

Other

OtherASME 2014 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2014
CountryUnited States
CityBuffalo
Period8/17/148/20/14

Keywords

  • Informatics
  • Machine learning
  • Material design
  • Microstructure descriptors

ASJC Scopus subject areas

  • Modeling and Simulation
  • Mechanical Engineering
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Fingerprint Dive into the research topics of 'A machine learning-based design representation method for designing heterogeneous microstructures'. Together they form a unique fingerprint.

Cite this