Detalhes bibliográficos
| Ano de defesa: |
2018 |
| Autor(a) principal: |
Delazzeri, Marcus Lessandro Costa
 |
| Orientador(a): |
Gadé, Anderson de Souza Matos
|
| Banca de defesa: |
Não Informado pela instituição |
| Tipo de documento: |
Dissertação
|
| Tipo de acesso: |
Acesso aberto |
| Idioma: |
por |
| Instituição de defesa: |
Universidade Estadual de Feira de Santana
|
| Programa de Pós-Graduação: |
Mestrado em Engenharia Civil e Ambiental
|
| Departamento: |
DEPARTAMENTO DE TECNOLOGIA
|
| País: |
Brasil
|
| Palavras-chave em Português: |
|
| Palavras-chave em Inglês: |
|
| Área do conhecimento CNPq: |
|
| Link de acesso: |
http://tede2.uefs.br:8080/handle/tede/828
|
Resumo: |
Artificial neural networks (ANN) have been shown to be an alternative computational mathematical tool for predicting the behavior of phenomena, including geotechnical engineering. In special its application in the study of the determination of the load capacity of piles. In this work, three models were developed for the prediction of load capacity, precast concrete and continuous flight hollow auger piles. For the construction of these models we used data collected in the technical literature, static load and dynamic loading tests, the geometry of piles and results of Standard Penetration Test SPT from different regions of Brazil and different types of soils. The predictive capacity of the models produced were measured comparingto the obtained results using the methods with the methodsAoki-Velloso (1975) and Décourt-Quaresma (1978), for precast concrete piles, and Aoki-Velloso (1975) and Décourt (1996) for continuous flight hollow auger piles. The results indicate that the models produced have high potential for the prediction of the load capacity of the evaluated piles, since the obtained results were shown similar errors to the studied methods. |
