PILE DRIVING RECORDS REANALYZED USING NEURAL NETWORKS

Pile driving formulas are commonly used to estimate the load capacity of driven piles. The formulas assume that there is a correlation betwe en the pile set and the ultimate load capacity of the pile. The import ant factors influencing the load capacity include the hammer character istics, the properties of the pile and soil, and the pile set. The pre sent technical note investigates the feasibility of using neural netwo rks to predict the load capacity of driven piles. Neural networks atte mpt to simulate the process by which the human brain learns to discern patterns in arrays of data. The data used in this study were derived from actual pile driving records. First, the neural network concepts a re reviewed, then the neural network model for predicting the pile cap acity is presented. The neural network predictions were found to be mo re consistent and reliable than other, more conventional pile driving formulas.