HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Engineering / Faculty of Engineering >
Peer-reviewed Journal Articles, etc >


Files in This Item:
Tetsu-to-Hagane 103(12) 720.pdf2.74 MBPDFView/Open
Please use this identifier to cite or link to this item:

Title: 機械学習によるミクロ偏析予測とマクロ偏析シミュレーションへの拡張
Other Titles: Prediction of Microsegregation Based on Machine Learning and Its Extension to a Macrosegregation Simulation
Authors: 大野, 宗一1 Browse this author →KAKEN DB
木村, 大地2 Browse this author
松浦, 清隆3 Browse this author →KAKEN DB
Authors(alt): Ohno, Munekazu1
Kimura, Daichi2
Matsuura, Kiyotaka3
Keywords: microsegregation
deep learning
phase-field simulation
Issue Date: 1-Dec-2017
Publisher: 日本鉄鋼協会
Journal Title: 鉄と鋼
Volume: 103
Issue: 12
Start Page: 720
End Page: 729
Publisher DOI: 10.2355/tetsutohagane.TETSU-2017-040
Abstract: An approach of machine learning called Deep Learning is utilized for construction of a prediction method of microsegregation behavior in Fe-based binary alloys with solute atoms of C, Si, Mn and P. Training data for the machine learning are obtained by quantitative phase-field simulations for directional solidification. Therefore, effects of microstructural evolutions on the microsegregation behavior are taken into account in the present method. Importantly, this method can be coupled with a macrosegregation model. The simulation result of the macrosegregation model is quite different from those obtained by a conventional macrosegregation model with the Scheil model and a model with a prediction method constructed from the training data of one-dimensional finite difference calculations for the microsegregation. This fact highlights the importance of accurate description of microsegregation behavior in prediction of macrosegregation.
Rights: 著作権は日本鉄鋼協会にある
Type: article
Appears in Collections:工学院・工学研究院 (Graduate School of Engineering / Faculty of Engineering) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

Submitter: 大野 宗一

Export metadata:

OAI-PMH ( junii2 , jpcoar )

MathJax is now OFF:


 - Hokkaido University