Comparison of Optimal Designs of Experiments in Application to Sensitivity and Inverse Analysis
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21110%2F12%3A00198943" target="_blank" >RIV/68407700:21110/12:00198943 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Comparison of Optimal Designs of Experiments in Application to Sensitivity and Inverse Analysis
Original language description
Nowadays the numerical models of structures and materials are more precise, but still time-consuming. Despite the growth of a computational effort, the exploration of model behaviour requires some basic tools. One of them is the sensitivity analysis investigating the sensitivity of the model to its inputs. Another tool often used in inverse analysis is meta-modelling replacing an exhaustive simulation by an approximation. Strategies to assess the sensitivity and/or build an approximation are usually based on a finite set of simulations for a given sets of input parameters, i.e. the design of experiments. This paper reviews criteria defining optimal designs of experiments and compares their quality in sampling-based sensitivity analysis and in neural network training process.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JM - Structural engineering
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/GPP105%2F11%2FP370" target="_blank" >GPP105/11/P370: Artificial neural networks in multi-scale modelling of transport processes in heterogeneous materials</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2012
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 3rd Conference Nano and Macro Mechanics NMM 2012
ISBN
978-80-01-05097-2
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
95-102
Publisher name
České vysoké učení technické v Praze, Fakulta stavební
Place of publication
Praha
Event location
Prague
Event date
Sep 20, 2012
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—