Neural networks assessment of beam-to-column joints
AUTOR(ES)
Lima, L. R. O. de, Vellasco, P. C. G. da S., Andrade, S. A. L. de, Silva, J. G. S. da, Vellasco, M. M. B. R.
FONTE
Journal of the Brazilian Society of Mechanical Sciences and Engineering
DATA DE PUBLICAÇÃO
2005-09
RESUMO
This paper proposes the use of artificial neural networks to predict the flexural resistance and initial stiffness of beam-to-column steel joints using the back propagation supervised learning algorithm. Three types of steel beam-to-column joints were investigated: welded, endplate and bolted with top, seat and double web angles, respectively. The neural networks results proved to be consistent with experimental and design code reference values.
Documentos Relacionados
- Classification System for Semi-Rigid Beam-to-Column Connections
- Análise numérica de ligações metálicas viga-coluna com coluna tubular circular
- Estimation of RC slab-column joints effective strength using neural networks
- Análise teórica e experimental de ligações viga mista-pilar de extremidade com cantoneiras de assento e alma
- Análise experimental estática e dinâmica da rigidez de ligações viga-pilar de concreto pré-moldado