Neural Network Model for Predicting the Resistance of Driven Piles

Abstract

Although numerous investigations have been performed over the years to predict the behavior and resistance of piles, the mechanisms are not yet entirely understood. Predicting pile resistance is a difficult task because there are a large number of parameters affecting the capacity that have complex relationships with each other. It is extremely difficult to develop appropriate relationships between various essential parameters, including the soil condition, pile type, driving condition, time effect, and others. This paper describes the application of an artificial neural network (ANN) to predict the resistance of driven piles in dynamic load tests. The training and testing of the ANN were based on 165 data points for driven piles at various construction sites in Korea. Predictions on the tip, shaft, and total pile resistance were made for piles with available corresponding measurements of such values. The effect of the essential parameters on the pile resistance values was investigated through parametric analysis using ANN modeling. The results of this study indicate that the ANN model serves as a reliable and simple predictive tool to appropriately consider various essential parameters for predicting the resistance of driven piles.

Keywords:

• ANN
• artificial neural network
• bearing capacity
• driven pile
• resistance

Notes

*For the type of pile tip, 0 represents a closed-ended tip and 1 represents an open-ended one.

*Matrix W1 (8 × 7), B1 (8 × 1), W2 (3 × 8), and B2 (3 × 1) is used in Eq. (2).