Artificial Intelligence Techniques for the
Design and Analysis of Deep Foundations
N. O. Nawari, R. Liang, and J. Nusairat
Department of Civil Engineering,
University of Akron, Akron, OH, USA
ABSTRACT
|
|
Artificial Intelligence Techniques for the N. O. Nawari, R. Liang, and J. Nusairat Department of Civil Engineering, | |
|
ABSTRACT |
Artificial intelligence paradigms are implemented to simulate the behavior of axially and laterally loaded piles, using data from full-scale drilled shaft and driven pile tests as well as from published data.
The main objective is to develop optimal neural network models using only simple input data. These data include SPT-N values and the geometrical properties. Neural network models are developed for steel H-piles, steel pipe piles, and pre-stressed and reinforced concrete piles. The models involved are Backpropagation, and Generalized Regression Neural Networks. Prediction results and comparison with the commonly used design methods are presented. Advantages and limitations of using neural networks in the design of pile foundations have been addressed.
Keywords: Artificial intelligence, piles, axial load, lateral load, analysis
