Please use this identifier to cite or link to this item:
http://hdl.handle.net/20.500.12358/19178
Title | Prediction of Ultimate Shear Strength of Reinforced Concrete Deep Beams Using Artificial Neural Networks |
---|---|
Untitled | |
Abstract |
The artificial neural networks (ANN) was used to develop a number of models in order to predict the ultimate shear strength of reinforced concrete deep beams for both normal and high concrete compressive strength. In this study a large number of experimental results database was collected carefully from previous studies. This database contained 161 and 42 experimental results for normal and high strength respectively. From the performed literature review a number of 7 variables were identified as input parameters for the ANN model for both normal and high strength concrete, whereas the output parameter was the ultimate shear strength. The feed forward back propagation neural network was used to build up the required model. Using the trial and error technique the topology of the neural networks was obtained. The ANN model was found to successfully predict the ultimate shear strength of deep beams within the range of the considered input parameters. The average ratio of the experimental shear strength to predicted shear strength using the ANN model is 1.04 for normal strength concrete and 1.002 for high strength concrete. The ANN shear strength predicted results were also compared to those obtained using the American Concrete Institute (ACI) code 318.02. The results show that ANN have strong potential as a feasible tool for predicting the ultimate shear strength of both normal and high strength RC deep beams within the range of input parameters. The trained neural network model was used to perform a parametric study to evaluate the effect of the input parameters on the utilized ultimate shear strength of deep beams. |
Authors | |
Supervisors | |
Type | رسالة ماجستير |
Date | 2005 |
Language | English |
Publisher | the islamic university |
Citation | |
License | ![]() |
Collections | |
Files in this item | ||
---|---|---|
file_1.pdf | 1.048Mb |