Horizontal Bearing Capacity of Pile in Sand by Neural Networks

In this research the application of the artificial neural network to predict the lateral load capacity of short piles in sand was studied. Piles with different diameter and length were considered as rigid and short piles so failure is due to soil governed criteria. Ultimate lateral load capasity was computed with theoretical method and results were compared to neural network predictions based on two criteria: the first one is the best fit line for predicted lateral load capacity (Qp) and computed lateral load capacity (Qc), and the second one is the cumulative probability for Qp/Qc. Different sesitivity analysis was discussed to identify the most important input parameters.

Keywords:

Pile , Lateral load , Neural Network