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 four-step machine learning-based method is developed to eliminate redundant microstructure descriptors via image analyses, to identify key microstructure descriptors based on structure–property 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 empirically chosen microstructure descriptors as a demonstration of the proposed method.
Skip Nav Destination
Article navigation
Research-Article
A Machine Learning-Based Design Representation Method for Designing Heterogeneous Microstructures Available to Purchase
Hongyi Xu,
Hongyi Xu
Department of Mechanical Engineering,
e-mail: [email protected]
Northwestern University
,Evanston, IL 60208
e-mail: [email protected]
Search for other works by this author on:
Ruoqian Liu,
Ruoqian Liu
Department of Electrical Engineering
and Computer Science,
e-mail: [email protected]
and Computer Science,
Northwestern University
,Evanston, IL 60208
e-mail: [email protected]
Search for other works by this author on:
Alok Choudhary,
Alok Choudhary
Department of Electrical Engineering
and Computer Science,
e-mail: [email protected]
and Computer Science,
Northwestern University
,Evanston, IL 60208
e-mail: [email protected]
Search for other works by this author on:
Wei Chen
Wei Chen
1
Department of Mechanical Engineering,
e-mail: [email protected]
Northwestern University
,Evanston, IL 60208
e-mail: [email protected]
1Corresponding author.
Search for other works by this author on:
Hongyi Xu
Department of Mechanical Engineering,
e-mail: [email protected]
Northwestern University
,Evanston, IL 60208
e-mail: [email protected]
Ruoqian Liu
Department of Electrical Engineering
and Computer Science,
e-mail: [email protected]
and Computer Science,
Northwestern University
,Evanston, IL 60208
e-mail: [email protected]
Alok Choudhary
Department of Electrical Engineering
and Computer Science,
e-mail: [email protected]
and Computer Science,
Northwestern University
,Evanston, IL 60208
e-mail: [email protected]
Wei Chen
Department of Mechanical Engineering,
e-mail: [email protected]
Northwestern University
,Evanston, IL 60208
e-mail: [email protected]
1Corresponding author.
Contributed by the Design Automation Committee of ASME for publication in the JOURNAL OF MECHANICAL DESIGN. Manuscript received August 21, 2014; final manuscript received February 3, 2015; published online March 5, 2015. Assoc. Editor: Carolyn Seepersad.
J. Mech. Des. May 2015, 137(5): 051403 (10 pages)
Published Online: May 1, 2015
Article history
Received:
August 21, 2014
Revision Received:
February 3, 2015
Online:
March 5, 2015
Citation
Xu, H., Liu, R., Choudhary, A., and Chen, W. (May 1, 2015). "A Machine Learning-Based Design Representation Method for Designing Heterogeneous Microstructures." ASME. J. Mech. Des. May 2015; 137(5): 051403. https://doi.org/10.1115/1.4029768
Download citation file:
Get Email Alerts
Related Articles
A Descriptor-Based Design Methodology for Developing Heterogeneous
Microstructural Materials System
J. Mech. Des (May,2014)
Hierarchical Design of Negative Stiffness Metamaterials Using a Bayesian Network Classifier
J. Mech. Des (April,2016)
Analysis and Design of Protein Based Nanodevices: Challenges and Opportunities in Mechanical Design
J. Mech. Des (July,2005)
High Temperature Fatigue of Welded Joints—Experimental Investigation and Local Analysis of Butt Welded Flat and Cruciform Specimens
J. Pressure Vessel Technol (August,2017)
Related Proceedings Papers
Related Chapters
Introduction and Definitions
Handbook on Stiffness & Damping in Mechanical Design
A New Structure of High Precision Extensometer
International Conference on Instrumentation, Measurement, Circuits and Systems (ICIMCS 2011)
Implementation and Research of NAS of TD-LTE Terminal
International Conference on Instrumentation, Measurement, Circuits and Systems (ICIMCS 2011)