Revue: | Journal of the Brazilian Society of Mechanical Sciences and Engineering |
Base de datos: | PERIÓDICA |
Número de sistema: | 000312269 |
ISSN: | 1678-5878 |
Autores: | Lima, L.R.O. de1 Vellasco, P.C.G. da S Andrade, S.A.L. de Silva, J.G.S. da Vellasco, M.M.B.R2 |
Instituciones: | 1Universidade do Estado do Rio de Janeiro, Faculdade de Engenharia, Rio de Janeiro. Brasil 2Pontificia Universidade Catolica do Rio de Janeiro, Departamento de Engenharia Eletrica, Rio de Janeiro. Brasil |
Año: | 2005 |
Periodo: | Jul-Sep |
Volumen: | 27 |
Número: | 3 |
Paginación: | 314-324 |
País: | Brasil |
Idioma: | Inglés |
Tipo de documento: | Artículo |
Enfoque: | Experimental |
Resumen en inglés | 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 |
Disciplinas: | Ingeniería, Ciencias de la computación |
Palabras clave: | Ingeniería civil, Ingeniería de control, Ingeniería mecánica, Redes neuronales artificiales, Estructuras de acero, Acero, Juntas semi-rígidas, Flexión |
Keyword: | Engineering, Computer science, Civil engineering, Control engineering, Mechanical engineering, Structural engineering, Semi-rigid joints, Steel structures, Artificial neural networks, Steel, Flexure |
Texte intégral: | Texto completo (Ver HTML) |