English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Machine-learning-based surrogate modeling of microstructure evolution using phase-field

Peivaste, I., Hamidi Siboni, N., Alahyarizadeh, G., Ghaderi, R., Svendsen, B., Raabe, D., et al. (2022). Machine-learning-based surrogate modeling of microstructure evolution using phase-field. Computational Materials Science, 214: 111750. doi:10.1016/j.commatsci.2022.111750.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Peivaste, Iman1, Author
Hamidi Siboni, Nima2, Author           
Alahyarizadeh, Ghasem1, Author
Ghaderi, Reza3, Author
Svendsen, Bob2, 4, Author           
Raabe, Dierk2, 5, Author           
Mianroodi, Jaber Rezaei6, 7, Author           
Affiliations:
1Faculty of Engineering, Shahid Beheshti University, Tehran, Iran, ou_persistent22              
2Microstructure Physics and Alloy Design, Max-Planck-Institut für Eisenforschung GmbH, Max Planck Society, ou_1863381              
3Department of Electrical Engineering, Shahid Beheshti University, Tehran, Iran, ou_persistent22              
4Material Mechanics, Faculty of Georesources and Materials Engineering, RWTH Aachen University, Schinkelstraße 2, D-52062 Aachen, Germany , ou_persistent22              
5Sustainable Synthesis of Materials, Interdepartmental and Partner Groups, Max-Planck-Institut für Eisenforschung GmbH, Max Planck Society, ou_3289784              
6Computational Sustainable Metallurgy, Microstructure Physics and Alloy Design, Max-Planck-Institut für Eisenforschung GmbH, Max Planck Society, ou_3243050              
7Theory and Simulation, Microstructure Physics and Alloy Design, Max-Planck-Institut für Eisenforschung GmbH, Max Planck Society, ou_1863392              

Content

show
hide
Free keywords: Machine learning, Deep learning, Convolutional neural network, U-Net, Phase-field, Grain growth, Allen–Cahn, Fan–Chen
 Abstract: Phase-field-based models have become common in material science, mechanics, physics, biology, chemistry, and engineering for the simulation of microstructure evolution. Yet, they suffer from the drawback of being computationally very costly when applied to large, complex systems. To reduce such computational costs, a Unet-based artificial neural network is developed as a surrogate model in the current work. Training input for this network is obtained from the results of the numerical solution of initial–boundary-value problems (IBVPs) based on the Fan–Chen model for grain microstructure evolution. In particular, about 250 different simulations with varying initial order parameters are carried out and 200 frames of the time evolution of the phase fields are stored for each simulation. The network is trained with 90% of this data, taking the ith frame of a simulation, i.e. order parameter field, as input, and producing the (i+1)-th frame as the output. Evaluation of the network is carried out with a test dataset consisting of 2200 microstructures based on different configurations than originally used for training. The trained network is applied recursively on initial order parameters to calculate the time evolution of the phase fields. The results are compared to the ones obtained from the conventional numerical solution in terms of the errors in order parameters and the system’s free energy. The resulting order parameter error averaged over all points and all simulation cases is 0.005 and the relative error in the total free energy in all simulation boxes does not exceed 1%.

Details

show
hide
Language(s): eng - English
 Dates: 2022-11
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: DOI: 10.1016/j.commatsci.2022.111750
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Computational Materials Science
  Abbreviation : Comput. Mater. Sci.
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Amsterdam : Elsevier
Pages: - Volume / Issue: 214 Sequence Number: 111750 Start / End Page: - Identifier: ISSN: 0927-0256
CoNE: https://pure.mpg.de/cone/journals/resource/954925567766