Prediction of Stress-Strain Curve of Block Copolymers Using Transfer Learning of 3D Convolutional Neural Network.

• KAWAGUCHI Hironobu

  Graduate School of Artificial Intelligence and Science, Rikkyo University,

• ITO Mariko I.

  Graduate School of Artificial Intelligence and Science, Rikkyo University,

• AOYAGI Takeshi

  Research Center for Computational Design of Advanced Functional Materials, National Institute of Advanced Industrial Science and Technology (AIST)

• OHNISHI Takaaki

  Graduate School of Artificial Intelligence and Science, Rikkyo University,

Bibliographic Information

Other Title

• 3次元畳み込みニューラルネットワークの転移学習を用いたブロック共重合体の応力ひずみ曲線予測

Abstract

The simulation to obtain stress-strain curves of block copolymers requires large computational resources. As an alternative to simulation, a method for high-throughput prediction of stress-strain curves using a three-dimensional convolutional neural network has been reported. In this study, we incorporated shortcut coupling into the neural network and performed pre-training and transfer learning in a step-by-step manner to successfully predict the stress-strain curve with high accuracy while reducing the training cost.

Journal

• Journal of Computer Chemistry, Japan

  Journal of Computer Chemistry, Japan 20 (3), 100-102, 2021

  Society of Computer Chemistry, Japan

Keywords

• Block copolymers
• Microphase separation
• Stress-strain curve
• Deep learning
• 3D convolutional neural network

Details

• CRID: 1390571704643088512
• NII Article ID: 130008122399
• DOI: 10.2477/jccj.2021-0037
• ISSN: 13473824
• ISSN: 13471767
• Web Site: https://www.jstage.jst.go.jp/article/jccj/20/3/20_2021-0037/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed