Coupling of scales in a multiscale simulation using neural networks
Multiscale approaches require the coupling of models on different spatial scales. In this paper, a coupling using neural networks is proposed. Based on a set of mesoscale simulations of concrete a system of neural networks is trained to approximate the response. A macroscale constitutive model is ob...
Saved in:
Published in | Computers & structures Vol. 86; no. 21; pp. 1994 - 2003 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
Kidlington
Elsevier Ltd
01.11.2008
Elsevier |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Multiscale approaches require the coupling of models on different spatial scales. In this paper, a coupling using neural networks is proposed. Based on a set of mesoscale simulations of concrete a system of neural networks is trained to approximate the response. A macroscale constitutive model is obtained by homogenizing the mesoscale response. Special focus is put on the mesh sensitivity, since the mesoscale model includes softening and consequently the width of the localization zone compared to the dimension of the mesoscale model is an additional parameter in the model. |
---|---|
Bibliography: | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 |
ISSN: | 0045-7949 1879-2243 |
DOI: | 10.1016/j.compstruc.2008.05.004 |