000022261 001__ 22261
000022261 005__ 20170622150004.0
000022261 04107 $$aeng
000022261 046__ $$k2015-05-25
000022261 100__ $$aFragiadakis, Michalis
000022261 24500 $$aQUICK SEISMIC RELIABILITY ASSESSMENT OF LIQUID STORAGE TANKS USING NEURAL NETWORKS

000022261 24630 $$n5.$$pComputational Methods in Structural Dynamics and Earhquake Engineering
000022261 260__ $$bNational Technical University of Athens, 2015
000022261 506__ $$arestricted
000022261 520__ $$2eng$$aLarge-capacity atmospheric tanks are widely used to store liquids, such as oil or liquefied natural gas. The seismic risk of such industrial facilities is considerably higher compared to ordinary structures, since even some minor damage induced by a ground motion may and/or manufacturing errors may have uncontrollable consequences, not only on the tank but also on the environment. Thus, aleatory and epistemic sources of uncertainty must be taken into consideration in order to provide a solid and realistic framework for the reliability analysis of liquid storage tanks. Incremental Dynamic Analysis (IDA) is a powerful method for the seismic performance assessment of structures. IDA is also very efficient for handling epistemic uncertainty, i.e. uncertainty due to the mechanical properties of the structure. In the latter case, IDA should be performed within a Monte Carlo framework requiring the execution of a vast number of nonlinear response history analyses. The increased computing effort renders the calculation of performance statistics time-consuming and hence the method is not always practical. We propose a scheme based on artificial neural networks (NN) in order to reduce the computational effort for the seismic reliability assessment of liquid storage tanks. Within a Monte Carlo framework, trained Neural networks can rapidly generate a large sample of IDA curves and therefore allow us to easily calculate useful response statistics. The implementation of the proposed approach is quick, straightforward and accurate.

000022261 540__ $$aText je chráněný podle autorského zákona č. 121/2000 Sb.
000022261 653__ $$a

000022261 7112_ $$aCOMPDYN 2015 - 5th International Thematic Conference$$cCrete (GR)$$d2015-05-25 / 2015-05-27$$gCOMPDYN2015
000022261 720__ $$aFragiadakis, Michalis$$iPapadopoulos, Vissarion$$iGiovanis, Dimitrios
000022261 8560_ $$ffischerc@itam.cas.cz
000022261 8564_ $$s9398$$uhttps://invenio.itam.cas.cz/record/22261/files/C1760_abstract.pdf$$yOriginal version of the author's contribution as presented on CD, section: 
.
000022261 962__ $$r22030
000022261 980__ $$aPAPER