2013
DOI: 10.1108/compel-10-2012-0205
|View full text |Cite
|
Sign up to set email alerts
|

Neural-FEM approach for the analysis of hysteretic materials in unbounded domain

Abstract: Purpose -This paper aims the application of a novel synergy between a neural network (NN) and the finite element method (FEM) in the solution of electromagnetic problem involving hysteretic material in unbounded domain. Design/methodology/approach -The hysteretic nature of the material is taken into account by an original NN able to perform the modelling of any kind of quasi-static loop (saturated and non-saturated, symmetric or asymmetric). An appositely developed iterative FEM procedure is presented for the … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
1
0

Year Published

2015
2015
2023
2023

Publication Types

Select...
3
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(1 citation statement)
references
References 15 publications
(15 reference statements)
0
1
0
Order By: Relevance
“…22 for obtaining an optimal number of neurons. [23][24][25][26][27][28] Figures 5 and 6 show the comparison between the experimental data and the predicted values of H by NS on test sets (i.e., on data not belonging to training sets) composed by three loops of H and B. Set up time was 15 min for experimental measurements and on a Intel Core i5-480M notebook based PC, the training time for each case was about 5 min and the successive prediction of the test loops took few seconds.…”
mentioning
confidence: 99%
“…22 for obtaining an optimal number of neurons. [23][24][25][26][27][28] Figures 5 and 6 show the comparison between the experimental data and the predicted values of H by NS on test sets (i.e., on data not belonging to training sets) composed by three loops of H and B. Set up time was 15 min for experimental measurements and on a Intel Core i5-480M notebook based PC, the training time for each case was about 5 min and the successive prediction of the test loops took few seconds.…”
mentioning
confidence: 99%