Object structure
Title:

Genetic algorithm and neural network methods for inverse problems of coupled models using topological derivative

Subtitle:

Raport Badawczy = Research Report ; RB/30/2017

Creator:

Lipnicka, Marta ; Szulc, Katarzyna ; Żochowski, Antoni

Publisher:

Instytut Badań Systemowych. Polska Akademia Nauk ; Systems Research Institute. Polish Academy of Sciences

Place of publishing:

Warszawa

Date issued/created:

2017

Description:

16 pages ; 21 cm ; Bibliography p. 15-16

Subject and Keywords:

Sieci neuronowe ; Optymalizacja kształtu ; Shape optimization ; Topological derivative ; Pochodna topologiczna ; Neural networks

Abstract:

This article compares two methods based on genetic algorithm and neural network for finding the location of small holes in the domain, in which the coupled boundary value problem is defined. The initial domain consists of two components, linear and nonlinear, connected by the transmission conditions defined at the interface boundary. Both methods: genetic algorithm and neural network calculate the location of one, two or three holes located somewhere in the linear part of the domain based on imput data coming from the exterior part of the domain.

Relation:

Raport Badawczy = Research Report

Resource type:

Text

Detailed Resource Type:

Report

Source:

RB-2017-30

Language:

eng

Language of abstract:

eng

Rights:

Creative Commons Attribution BY 4.0 license

Terms of use:

Copyright-protected material. [CC BY 4.0] May be used within the scope specified in Creative Commons Attribution BY 4.0 license, full text available at: ; -

Digitizing institution:

Systems Research Institute of the Polish Academy of Sciences

Original in:

Library of Systems Research Institute PAS

Projects co-financed by:

Operational Program Digital Poland, 2014-2020, Measure 2.3: Digital accessibility and usefulness of public sector information; funds from the European Regional Development Fund and national co-financing from the state budget.

Access:

Open

×

Citation

Citation style: