Lateral pressures on non-yielding walls due to surface strip loads were
investigated considering the non-linear stress-strain behaviour of the soil by finite
element analyses. Data obtained from the finite element analyses were used to
train neural networks in order to obtain a solution to assess the total lateral thrust
and its point of application on a non-yielding wall due to a strip load. A 2-layered
backpropogation type neural network was used. An artificial neural network
solution was obtained, as a function of six parameters including the shear strength
parameters of the soil ( cohesion and angle of friction ). The effects of each input
parameter on the lateral thrust and point of application were summarized and the
results were compared with the conventional linear elastic solution.
| Identifer | oai:union.ndltd.org:METU/oai:etd.lib.metu.edu.tr:http://etd.lib.metu.edu.tr/upload/1264415/index.pdf |
| Date | 01 January 2003 |
| Creators | Yildiz, Ersan |
| Contributors | Ozkan, M. Yener |
| Publisher | METU |
| Source Sets | Middle East Technical Univ. |
| Language | English |
| Detected Language | English |
| Type | M.S. Thesis |
| Format | text/pdf |
| Rights | To liberate the content for public access |
Page generated in 0.0018 seconds