機械学習を用いた結晶成長予測モデルの構築とその応用

宇治原 徹; 角岡 洋介; 畑佐 豪記; 沓掛 健太朗; 石黒 祥生; 村山 健太; 鳴海 大翔; 原田 俊太; 田川 美穂

doi:10.1380/vss.62.136

Special Feature : Research Forefront of Surface and Vacuum Science Developed by Data-Driven Approach

The Prediction Model of Crystal Growth Simulation Built by Machine Learning and Its Applications

Toru UJIHARA , Yosuke TSUNOOKA, Goki HATASA, Kentaro KUTSUKAKE, Akio ISHIGURO, Kenta MURAYAMA, Taka NARUMI, Shunta HARADA, Miho TAGAWA

Author information

Toru UJIHARA Corresponding author
Institute of Materials and Systems for Sustainability (IMaSS), Nagoya University
GaN-OIL, National Institute of Advanced Industrial Science and Technology (AIST)
Department of Materials Process Engineering, Nagoya University
Center for dvanced Intelligence Project (AIP), RIKEN
Yosuke TSUNOOKA
GaN-OIL, National Institute of Advanced Industrial Science and Technology (AIST)
Department of Materials Process Engineering, Nagoya University
Goki HATASA
Department of Materials Process Engineering, Nagoya University
Kentaro KUTSUKAKE
Institute of Materials and Systems for Sustainability (IMaSS), Nagoya University
Center for dvanced Intelligence Project (AIP), RIKEN
Akio ISHIGURO
Institute of Innovation for Future Society, Nagoya University
Kenta MURAYAMA
Institute of Materials and Systems for Sustainability (IMaSS), Nagoya University
Taka NARUMI
Institute of Materials and Systems for Sustainability (IMaSS), Nagoya University
Shunta HARADA
Institute of Materials and Systems for Sustainability (IMaSS), Nagoya University
Department of Materials Process Engineering, Nagoya University
Miho TAGAWA
Institute of Materials and Systems for Sustainability (IMaSS), Nagoya University
Department of Materials Process Engineering, Nagoya University

Keywords: crystal growth, machine learning, optimization, visualization, silicon carbide

JOURNAL FREE ACCESS

2019 Volume 62 Issue 3 Pages 136-140

DOI https://doi.org/10.1380/vss.62.136

Details

Abstract

The prediction model of the result of computed fluid dynamics simulation in SiC solution growth was constructed on neural network using machine learning. Utilizing the prediction model, we can optimize quickly crystal growth conditions. In addition, the real-time visualization system was also made using the prediction model.

Fullsize Image

Corresponding author

Register with J-STAGE for free!