Optimized Neural Network Model For The Prediction Of Driven Pile's Resistance

Although numerous investigations have been performed over the years to predict the behavior and bearing capacity of piles, the mechanisms of these behavior and bearing capacity of piles have yet to be entirely understood. Bearing capacity is difficult to predict, because it is affected by many parameters, which have complex relationship with each other. The present paper describes the application of Artificial Neural Network (ANN) in dynamic load tests to predict the resistance of driven piles. The tip, shaft, and total pile resistances can be predicted only for piles with available corresponding measurements of these values. The design methodology composed of ANN and genetic algorithm (GA) is applied to find the optimal neural network model to predict pile resistance. The results of this study indicate that the neural network model serves as a reliable and simple tool for predicting the capacity of driven piles.