Neural networks in 3-dimensional dynamic analysis of reinforced concrete buildings

The objective of this study is to investigate the adequacy of Artificial Neural Networks (ANN) as a securer, quicker and more robust method to determine the dynamic response of buildings in 3D. For this purpose, two ANN models were proposed to estimate the fundamental periods, base shear force, base...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Construction & building materials Ročník 22; číslo 5; s. 788 - 800
Hlavní autoři: Caglar, Naci, Elmas, Muzaffer, Yaman, Zeynep Dere, Saribiyik, Mehmet
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.05.2008
Elsevier B.V
Témata:
Adequacy
Algorithms
Analysis
Artificial neural networks
Back propagation
Bays
Bending moments
Building materials industry
Buildings
Concrete construction
Conjugate gradients
Construction
Displacement
Dynamic analysis
Dynamic response
Dynamic tests
Dynamics
Earthquake construction
Estimates
Finite element method
Learning theory
Mathematical analysis
Mathematical models
Matlab
Moments of inertia
Multilayer perceptrons
Neural networks
Reinforced concrete
Response of buildings
Scaled conjugate gradient algorithm
Seismic phenomena
Shear
Three dimensional
Training
Scaled conjugate gradient algorithm
Neural networks
Response of buildings
Dynamic analysis
ISSN:0950-0618, 1879-0526
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The objective of this study is to investigate the adequacy of Artificial Neural Networks (ANN) as a securer, quicker and more robust method to determine the dynamic response of buildings in 3D. For this purpose, two ANN models were proposed to estimate the fundamental periods, base shear force, base bending moments and top-floor displacement of buildings in two directions. Total moment of inertia for each storey was defined in order to avoid limitation to describe the structure due to the number of columns, shear-walls and number of bays. The same input layer was submitted to different types of ANN models for various outcomes. In the ANN models, a multilayer perceptron (MLP) with a back-propagation (BP) algorithm was employed using a scaled conjugate gradient. ANN models were developed, trained and tested in a based MATLAB program. A training set of 150 and a validation set of 15 buildings were produced from dynamic response of different buildings. Finite Element Analysis (FEA) was used to generate training and testing set of ANN models. It was demonstrated that the neural network based approach is highly successful to determine response of buildings subjected to earthquake.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ObjectType-Article-2
ObjectType-Feature-1
ISSN:0950-0618
1879-0526
DOI:10.1016/j.conbuildmat.2007.01.029