TY - GEN
T1 - A machine learning-based design representation method for designing heterogeneous microstructures
AU - Xu, Hongyi
AU - Liu, Ruoqian
AU - Choudhary, Alok
AU - Chen, Wei
N1 - Publisher Copyright:
Copyright © 2014 by ASME.
PY - 2014
Y1 - 2014
N2 - 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.
AB - 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.
KW - Informatics
KW - Machine learning
KW - Material design
KW - Microstructure descriptors
UR - http://www.scopus.com/inward/record.url?scp=84961338577&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84961338577&partnerID=8YFLogxK
U2 - 10.1115/DETC201434570
DO - 10.1115/DETC201434570
M3 - Conference contribution
AN - SCOPUS:84961338577
T3 - Proceedings of the ASME Design Engineering Technical Conference
BT - 40th Design Automation Conference
PB - American Society of Mechanical Engineers (ASME)
T2 - ASME 2014 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2014
Y2 - 17 August 2014 through 20 August 2014
ER -