A NEURAL-NETWORK APPROACH TO THE MODELING, CALCULATION AND IDENTIFICATION OF SEMIRIGID CONNECTIONS IN STEEL STRUCTURES

Authors
STAVROULAKIS GE AVDELAS AV ABDALLA KM PANAGIOTOPOULOS PD
Citation
Ge. Stavroulakis et al., A NEURAL-NETWORK APPROACH TO THE MODELING, CALCULATION AND IDENTIFICATION OF SEMIRIGID CONNECTIONS IN STEEL STRUCTURES, Journal of constructional steel research, 44(1-2), 1997, pp. 91-105
Citations number
40
Journal title
Journal of constructional steel research → ACNP
ISSN journal
0143974X
Volume
44
Issue
1-2
Year of publication
1997
Pages
91 - 105
Database
ISI
SICI code
0143-974X(1997)44:1-2<91:ANATTM>2.0.ZU;2-Q
Abstract
A two-stage neural network approach is proposed for the elastoplastic analysis of steel structures with semi-rigid connections. At the first stage, the moment-rotation law of the connection is obtained from exp erimental results by the use of a neural network based on the perceptr on model. At the second stage, the elastoplastic analysis problem is f ormulated for the given moment-rotation law as a Quadratic Programming Problem and solved by a neural network based on the Hopfield model. ( C) 1997 Elsevier Science Ltd.