Neural network analysis of overturning response under near-fault type excitation

Gerolymos, N; Apostolou, M; Gazetas, G

dc.contributor.author	Gerolymos, N	en
dc.contributor.author	Apostolou, M	en
dc.contributor.author	Gazetas, G	en
dc.date.accessioned	2014-03-01T01:22:49Z
dc.date.available	2014-03-01T01:22:49Z
dc.date.issued	2005	en
dc.identifier.issn	16713664	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/16664
dc.subject	Kocaeli records	en
dc.subject	Near-fault motion	en
dc.subject	Neural network	en
dc.subject	Overturning	en
dc.subject	Pulse	en
dc.subject	Rocking spectrum	en
dc.subject	Uplifting	en
dc.subject.other	Computational geometry	en
dc.subject.other	Neural networks	en
dc.subject.other	Numerical analysis	en
dc.subject.other	Uplift pressure	en
dc.subject.other	Wavelet transforms	en
dc.subject.other	Kocaeli records	en
dc.subject.other	Overturning	en
dc.subject.other	Pulse	en
dc.subject.other	Uplifting	en
dc.subject.other	Seismology	en
dc.title	Neural network analysis of overturning response under near-fault type excitation	en
heal.type	journalArticle	en
heal.identifier.primary	10.1007/s11803-005-0004-0	en
heal.identifier.secondary	http://dx.doi.org/10.1007/s11803-005-0004-0	en
heal.identifier.secondary	1671-3664(2005)02-0213-16	en
heal.publicationDate	2005	en
heal.abstract	Under strong seismic excitation, a rigid block will uplift from its support and undergo rocking oscillations which may lead to (complete) overturning. Numerical and analytical solutions to this highly nonlinear vibration problem are first highlighted in the paper and then utilized to demonstrate how sensitive the overturning behavior is not only to the intensity and frequency content of the base motion, but also to the presence of strong pulses, to their detailed sequence, and even to their asymmetry. Five idealised pulses capable of representing ""rupture-directivity"" and ""fling"" affected ground motions near the fault, are utilized to this end : the one-cycle sinus, the one-cycle cosinus, the Ricker wavelet, the truncated (T)-Ricker wavelet, and the rectangular pulse ""Overturning-Acceleration Amplification"" and ""Rotation"" spectra are introduced and presented. Artificial neural network modeling is then developed as an alternative numerical solution. The neural network analysis leads to closed-form expressions for predicting the overturning failure or survival of a rigid block, as a function of its geometric properties and the characteristics of the excitation time history. The capability of the developed neural network modeling is validated through comparisons with the numerical solution. The derived analytical expressions could also serve as a tool for assessing the destructiveness of near-fault ground motions, for structures sensitive to rocking with foundation uplift.	en
heal.journalName	Earthquake Engineering and Engineering Vibration	en
dc.identifier.doi	10.1007/s11803-005-0004-0	en
dc.identifier.volume	4	en
dc.identifier.issue	2	en
dc.identifier.spage	213	en
dc.identifier.epage	228	en