A deep adversarial learning methodology for designing microstructural material systems

Xiaolin Li, Zijiang Yang, L. Catherine Brinson, Alok Nidhi Choudhary, Ankit Agrawal, Wei Chen*

*Corresponding author for this work

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

6 Citations (Scopus)

Abstract

In Computational Materials Design (CMD), it is well recognized that identifying key microstructure characteristics is crucial for determining material design variables. However, existing microstructure characterization and reconstruction (MCR) techniques have limitations to be applied for materials design. Some MCR approaches are not applicable for material microstructural design because no parameters are available to serve as design variables, while others introduce significant information loss in either microstructure representation and/or dimensionality reduction. In this work, we present a deep adversarial learning methodology that overcomes the limitations of existing MCR techniques. In the proposed methodology, generative adversarial networks (GAN) are trained to learn the mapping between latent variables and microstructures. Thereafter, the low-dimensional latent variables serve as design variables, and a Bayesian optimization framework is applied to obtain microstructures with desired material property. Due to the special design of the network architecture, the proposed methodology is able to identify the latent (design) variables with desired dimensionality, as well as capturing complex material microstructural characteristics. The validity of the proposed methodology is tested numerically on a synthetic microstructure dataset and its effectiveness for materials design is evaluated through a case study of optimizing optical performance for energy absorption. Additional features, such as scalability and transferability, are also demonstrated in this work. In essence, the proposed methodology provides an end-to-end solution for microstructural design, in which GAN reduces information loss and preserves more microstructural characteristics, and the GP-Hedge optimization improves the efficiency of design exploration.

Original languageEnglish (US)
Title of host publication44th Design Automation Conference
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791851760
DOIs
StatePublished - Jan 1 2018
EventASME 2018 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2018 - Quebec City, Canada
Duration: Aug 26 2018Aug 29 2018

Publication series

NameProceedings of the ASME Design Engineering Technical Conference
Volume2B-2018

Other

OtherASME 2018 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2018
CountryCanada
CityQuebec City
Period8/26/188/29/18

Fingerprint

Microstructure
Material Design
Methodology
Information Loss
Latent Variables
Energy Absorption
Learning
Deep learning
Optimization
Dimensionality Reduction
Network Architecture
Material Properties
Dimensionality
Design
Scalability
Energy absorption
Network architecture
Materials properties

Keywords

  • Bayesian optimization
  • Deep learning
  • Generative adversarial network
  • Materials design
  • Microstructural analysis
  • Scalability
  • Transfer learning

ASJC Scopus subject areas

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

Cite this

Li, X., Yang, Z., Catherine Brinson, L., Choudhary, A. N., Agrawal, A., & Chen, W. (2018). A deep adversarial learning methodology for designing microstructural material systems. In 44th Design Automation Conference (Proceedings of the ASME Design Engineering Technical Conference; Vol. 2B-2018). American Society of Mechanical Engineers (ASME). https://doi.org/10.1115/DETC201885633
Li, Xiaolin ; Yang, Zijiang ; Catherine Brinson, L. ; Choudhary, Alok Nidhi ; Agrawal, Ankit ; Chen, Wei. / A deep adversarial learning methodology for designing microstructural material systems. 44th Design Automation Conference. American Society of Mechanical Engineers (ASME), 2018. (Proceedings of the ASME Design Engineering Technical Conference).
@inproceedings{0c0360ef516e41c7a0091e042d512acf,
title = "A deep adversarial learning methodology for designing microstructural material systems",
abstract = "In Computational Materials Design (CMD), it is well recognized that identifying key microstructure characteristics is crucial for determining material design variables. However, existing microstructure characterization and reconstruction (MCR) techniques have limitations to be applied for materials design. Some MCR approaches are not applicable for material microstructural design because no parameters are available to serve as design variables, while others introduce significant information loss in either microstructure representation and/or dimensionality reduction. In this work, we present a deep adversarial learning methodology that overcomes the limitations of existing MCR techniques. In the proposed methodology, generative adversarial networks (GAN) are trained to learn the mapping between latent variables and microstructures. Thereafter, the low-dimensional latent variables serve as design variables, and a Bayesian optimization framework is applied to obtain microstructures with desired material property. Due to the special design of the network architecture, the proposed methodology is able to identify the latent (design) variables with desired dimensionality, as well as capturing complex material microstructural characteristics. The validity of the proposed methodology is tested numerically on a synthetic microstructure dataset and its effectiveness for materials design is evaluated through a case study of optimizing optical performance for energy absorption. Additional features, such as scalability and transferability, are also demonstrated in this work. In essence, the proposed methodology provides an end-to-end solution for microstructural design, in which GAN reduces information loss and preserves more microstructural characteristics, and the GP-Hedge optimization improves the efficiency of design exploration.",
keywords = "Bayesian optimization, Deep learning, Generative adversarial network, Materials design, Microstructural analysis, Scalability, Transfer learning",
author = "Xiaolin Li and Zijiang Yang and {Catherine Brinson}, L. and Choudhary, {Alok Nidhi} and Ankit Agrawal and Wei Chen",
year = "2018",
month = "1",
day = "1",
doi = "10.1115/DETC201885633",
language = "English (US)",
series = "Proceedings of the ASME Design Engineering Technical Conference",
publisher = "American Society of Mechanical Engineers (ASME)",
booktitle = "44th Design Automation Conference",

}

Li, X, Yang, Z, Catherine Brinson, L, Choudhary, AN, Agrawal, A & Chen, W 2018, A deep adversarial learning methodology for designing microstructural material systems. in 44th Design Automation Conference. Proceedings of the ASME Design Engineering Technical Conference, vol. 2B-2018, American Society of Mechanical Engineers (ASME), ASME 2018 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2018, Quebec City, Canada, 8/26/18. https://doi.org/10.1115/DETC201885633

A deep adversarial learning methodology for designing microstructural material systems. / Li, Xiaolin; Yang, Zijiang; Catherine Brinson, L.; Choudhary, Alok Nidhi; Agrawal, Ankit; Chen, Wei.

44th Design Automation Conference. American Society of Mechanical Engineers (ASME), 2018. (Proceedings of the ASME Design Engineering Technical Conference; Vol. 2B-2018).

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

TY - GEN

T1 - A deep adversarial learning methodology for designing microstructural material systems

AU - Li, Xiaolin

AU - Yang, Zijiang

AU - Catherine Brinson, L.

AU - Choudhary, Alok Nidhi

AU - Agrawal, Ankit

AU - Chen, Wei

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In Computational Materials Design (CMD), it is well recognized that identifying key microstructure characteristics is crucial for determining material design variables. However, existing microstructure characterization and reconstruction (MCR) techniques have limitations to be applied for materials design. Some MCR approaches are not applicable for material microstructural design because no parameters are available to serve as design variables, while others introduce significant information loss in either microstructure representation and/or dimensionality reduction. In this work, we present a deep adversarial learning methodology that overcomes the limitations of existing MCR techniques. In the proposed methodology, generative adversarial networks (GAN) are trained to learn the mapping between latent variables and microstructures. Thereafter, the low-dimensional latent variables serve as design variables, and a Bayesian optimization framework is applied to obtain microstructures with desired material property. Due to the special design of the network architecture, the proposed methodology is able to identify the latent (design) variables with desired dimensionality, as well as capturing complex material microstructural characteristics. The validity of the proposed methodology is tested numerically on a synthetic microstructure dataset and its effectiveness for materials design is evaluated through a case study of optimizing optical performance for energy absorption. Additional features, such as scalability and transferability, are also demonstrated in this work. In essence, the proposed methodology provides an end-to-end solution for microstructural design, in which GAN reduces information loss and preserves more microstructural characteristics, and the GP-Hedge optimization improves the efficiency of design exploration.

AB - In Computational Materials Design (CMD), it is well recognized that identifying key microstructure characteristics is crucial for determining material design variables. However, existing microstructure characterization and reconstruction (MCR) techniques have limitations to be applied for materials design. Some MCR approaches are not applicable for material microstructural design because no parameters are available to serve as design variables, while others introduce significant information loss in either microstructure representation and/or dimensionality reduction. In this work, we present a deep adversarial learning methodology that overcomes the limitations of existing MCR techniques. In the proposed methodology, generative adversarial networks (GAN) are trained to learn the mapping between latent variables and microstructures. Thereafter, the low-dimensional latent variables serve as design variables, and a Bayesian optimization framework is applied to obtain microstructures with desired material property. Due to the special design of the network architecture, the proposed methodology is able to identify the latent (design) variables with desired dimensionality, as well as capturing complex material microstructural characteristics. The validity of the proposed methodology is tested numerically on a synthetic microstructure dataset and its effectiveness for materials design is evaluated through a case study of optimizing optical performance for energy absorption. Additional features, such as scalability and transferability, are also demonstrated in this work. In essence, the proposed methodology provides an end-to-end solution for microstructural design, in which GAN reduces information loss and preserves more microstructural characteristics, and the GP-Hedge optimization improves the efficiency of design exploration.

KW - Bayesian optimization

KW - Deep learning

KW - Generative adversarial network

KW - Materials design

KW - Microstructural analysis

KW - Scalability

KW - Transfer learning

UR - http://www.scopus.com/inward/record.url?scp=85053003261&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053003261&partnerID=8YFLogxK

U2 - 10.1115/DETC201885633

DO - 10.1115/DETC201885633

M3 - Conference contribution

AN - SCOPUS:85053003261

T3 - Proceedings of the ASME Design Engineering Technical Conference

BT - 44th Design Automation Conference

PB - American Society of Mechanical Engineers (ASME)

ER -

Li X, Yang Z, Catherine Brinson L, Choudhary AN, Agrawal A, Chen W. A deep adversarial learning methodology for designing microstructural material systems. In 44th Design Automation Conference. American Society of Mechanical Engineers (ASME). 2018. (Proceedings of the ASME Design Engineering Technical Conference). https://doi.org/10.1115/DETC201885633