Application of Deep Learning in Materials Design: Extraction of Process-Structure-Property Relationship
-
- Noguchi Satoshi
- Research Institute for Value-Added-Information Generation, Japan Agency for Marine-Earth Science and Technology
-
- Wang Hui
- Institute for Industrial Science, The University of Tokyo
-
- Inoue Junya
- Institute for Industrial Science, The University of Tokyo
Bibliographic Information
- Other Title
-
- 材料設計における深層学習の応用:プロセス・構造・特性連関の抽出
- ザイリョウ セッケイ ニ オケル シンソウ ガクシュウ ノ オウヨウ : プロセス ・ コウゾウ ・ トクセイ レンカン ノ チュウシュツ
Search this article
Abstract
<p>In material design, the establishment of a process-structure-property linkage is indispensable for developing a general methodology for inverse material design and understanding the physical mechanisms behind material microstructure generation. In recent years, deep learning based methods have received much attention in the field of computational material design. Thus, we developed the general deep learning methodology for extraction of a process-structure-property linkage.Our approach can be divided into two parts: characterization of material microstructures by a vector quantized variational auto-encoder, and determination of the correlation between the extracted microstructure characterizations and the given conditions, such as processing parameters and/or material properties, by a pixel convolutional neural network. In this work, we present the following three our recent results: (i) extraction of the process-structure relationship of structural material by our deep learning framework, (ii) identification of a part of microstructures critically affecting the target property without giving the background physics, and (iii) molecular structure optimization by PixelCNN.</p>
Journal
-
- Ouyou toukeigaku
-
Ouyou toukeigaku 52 (2), 75-98, 2023
Japanese Society of Applied Statistics
- Tweet
Details 詳細情報について
-
- CRID
- 1390299207434341632
-
- NII Book ID
- AN00330942
-
- ISSN
- 18838081
- 02850370
-
- NDL BIB ID
- 033342541
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- Crossref
-
- Abstract License Flag
- Disallowed