Mimicking complex dislocation dynamics by interaction networks

Research output: Contribution to journalArticle

Standard

Mimicking complex dislocation dynamics by interaction networks. / Salmenjoki, Henri; Alava, Mikko J.; Laurson, Lasse.

In: European Physical Journal B, Vol. 91, No. 11, 275, 13.11.2018, p. 1-6.

Research output: Contribution to journalArticle

Harvard

APA

Vancouver

Author

Bibtex - Download

@article{38cfa126748145cdb0771cb5147eb60a,
title = "Mimicking complex dislocation dynamics by interaction networks",
abstract = "Two-dimensional discrete dislocation models exhibit complex dynamics in relaxation and under external loading. This is manifested both in the time-dependent velocities of individual dislocations and in the ensemble response, the strain rate. Here we study how well this complexity may be reproduced using so-called Interaction Networks, an artificial intelligence method for learning the dynamics of complex interacting systems. We test how to learn such networks using creep data, and show results on reproducing individual and collective dislocation velocities. The quality of reproducing the interaction kernel is discussed.",
keywords = "FLOW",
author = "Henri Salmenjoki and Alava, {Mikko J.} and Lasse Laurson",
year = "2018",
month = "11",
day = "13",
doi = "10.1140/epjb/e2018-90419-7",
language = "English",
volume = "91",
pages = "1--6",
journal = "European Physical Journal B. Condensed Matter and Complex Systems",
issn = "1434-6028",
number = "11",

}

RIS - Download

TY - JOUR

T1 - Mimicking complex dislocation dynamics by interaction networks

AU - Salmenjoki, Henri

AU - Alava, Mikko J.

AU - Laurson, Lasse

PY - 2018/11/13

Y1 - 2018/11/13

N2 - Two-dimensional discrete dislocation models exhibit complex dynamics in relaxation and under external loading. This is manifested both in the time-dependent velocities of individual dislocations and in the ensemble response, the strain rate. Here we study how well this complexity may be reproduced using so-called Interaction Networks, an artificial intelligence method for learning the dynamics of complex interacting systems. We test how to learn such networks using creep data, and show results on reproducing individual and collective dislocation velocities. The quality of reproducing the interaction kernel is discussed.

AB - Two-dimensional discrete dislocation models exhibit complex dynamics in relaxation and under external loading. This is manifested both in the time-dependent velocities of individual dislocations and in the ensemble response, the strain rate. Here we study how well this complexity may be reproduced using so-called Interaction Networks, an artificial intelligence method for learning the dynamics of complex interacting systems. We test how to learn such networks using creep data, and show results on reproducing individual and collective dislocation velocities. The quality of reproducing the interaction kernel is discussed.

KW - FLOW

U2 - 10.1140/epjb/e2018-90419-7

DO - 10.1140/epjb/e2018-90419-7

M3 - Article

VL - 91

SP - 1

EP - 6

JO - European Physical Journal B. Condensed Matter and Complex Systems

JF - European Physical Journal B. Condensed Matter and Complex Systems

SN - 1434-6028

IS - 11

M1 - 275

ER -

ID: 31444497