# Maximization of strength–ductility balance of dual-phase steels using generative adversarial networks and Bayesian optimization

https://mdr.nims.go.jp/datasets/6e4abd81-e403-47cd-9971-a5f516e3e7ae

## File

- [Manuscript_240826_R1.pdf](https://mdr.nims.go.jp/filesets/8fc10308-5436-42b1-a34d-307dbf942cfc/download) ([Detail](https://mdr.nims.go.jp/filesets/8fc10308-5436-42b1-a34d-307dbf942cfc.md))

## Id

6e4abd81-e403-47cd-9971-a5f516e3e7ae

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2024-09-25T01:26:55.472957Z

## Updated at

2024-09-25T01:53:57.146174Z

## Published at

2026-09-14T23:30:30.397078Z

## Doi

https://doi.org/10.48505/nims.4771

## First published url

https://doi.org/10.1016/j.mtcomm.2024.110360

## Date published

2024-09-15

## Recorded date published

2024-12

## Resource type

journal_article

## Manuscript type

accepted_manuscript

## Collection



## Title

- title: Maximization of strength–ductility balance of dual-phase steels using generative
    adversarial networks and Bayesian optimization
  title_type: original
  lang: en

## Description

- description: Dual-phase (DP) steels with a soft ferrite matrix and hard martensite
    islands exhibit an excellent combination of strength and ductility. However, further
    improvement of the strength–ductility balance is desirable for automotive applications,
    and the optimization of the DP microstructure is crucial for enhancing mechanical
    properties. This study aimed to maximize the strength–ductility balance of DP
    steel using an integrated computational framework comprised by generative adversarial
    networks (GAN), finite element method (FEM), and Bayesian optimization. GAN was
    trained on the microstructures of real DP steels to generate synthetic microstructure
    images randomly mapped from latent variable vectors, and the tensile properties
    of the generated microstructures were evaluated using FEM. Bayesian optimization
    was then employed to identify latent variables yielding microstructures with the
    highest tensile strength (TS), uniform elongation (uEL), or strength–ductility
    balance (TS × uEL). The optimized microstructures of DP steels were then quantitatively
    analyzed to elucidate the relationship between the microstructural morphology
    and tensile properties. The optimal synthetic DP microstructure exhibited a TS
    × uEL value higher by 4027 MPa% than the highest value shown by real DP steels.
    Thus, the proposed integrated optimization framework enables efficient computational
    design of various material microstructures for maximizing desired mechanical properties.
  description_type: abstract
  lang: und

## Creator

- name: Yoshihito Fukatsu
  role: author
  organization: Nagoya University
- name: Ta-Te Chen
  role: author
  organization: Nagoya University
- name: Toshio Ogawa
  role: author
  organization: Aichi Institute of Technology
- name: Fei Sun
  role: author
  organization: Nagoya University
- name: Ikumu Watanabe
  role: author
  orcid: https://orcid.org/0000-0002-7693-1675
  organization: National Institute for Materials Science
  ror: https://ror.org/026v1ze26
- name: Mayumi Ojima
  role: author
  organization: JFE Steel Corporation
- name: Shin Ishikawa
  role: author
  organization: JFE Steel Corporation
- name: Yoshitaka Adachi
  role: author
  organization: Nagoya University

## Contact agent



## Publisher

organization: Elsevier BV

## Managing organization



## Keyword

- subject: Dual-phase steel
  schema: not_defined
- subject: Strength–ductility balance
  schema: not_defined
- subject: Generative adversarial networks
  schema: not_defined
- subject: Bayesian optimization
  schema: not_defined

## Rights

- identifier: https://creativecommons.org/licenses/by-nc-nd/4.0/

## Other identifier(s)



## Data origin

- data_origin_type: other

## Embargo

start_date: 2024-09-15
end_date: 2026-09-15

## Journal

- title: Materials Today Communications
  issn: '23524928'
  volume: '41'
  article_number: '110360'

## Conference



## Related item



## Funding

- identifier: 22H01807
  funder_name: Japan Society for the Promotion of Science

## Instrument



## Instrument operator



## Instrument managing organization



## Measurement method



## Specimen



## Chemical composition



## Structure for specimen



## Structural feature for specimen



## Specific property for specimen



## Process for specimen treatment



## Computational method



## Energy level/transition state



## Software



## Custom property



## Fileset

- id: 8fc10308-5436-42b1-a34d-307dbf942cfc
  filename: Manuscript_240826_R1.pdf
  content_type: application/pdf
  size: 6586982
  md5: 04b6f8a699f6779d89c0b82472ecf359

## Thumbnail

fileset_id: 8fc10308-5436-42b1-a34d-307dbf942cfc
filename: Manuscript_240826_R1.pdf