Shaft Resistance of Driven Piles Based on CPT and CPTu Results Using GMDH-type Neural Networks and Genetic Algorithms

Cone penetration test is one of the most common in-situ tests for pile analysis given that by its analogy as a model pile, the measured cone resistance and sleeve friction can be employed for estimation of pile unit toe and shaft resistances, respectively. In this paper, group method of data handling (GMDH)-type neural networks optimized using Genetic algorithms (GAs) are used for modelling the effects of effective cone point resistance (Equ) and cone sleeve friction (fs) as input parameters on driven piles unit shaft resistance, using some experimental training and test data. Therefore twenty two pile case histories have been compiled including static loading tests performed in uplift, or in push with separation of shaft and toe resistances at sites which comprise CPT or CPTu sounding. Sensitivity analysis of the derived polynomial model has been carried out to study the influence of input parameters on model output. Some curves have been found to estimate driven piles unit shaft resistance using obtained results from sensitivity analysis. Comparison between proposed method and other CPT and CPTu direct methods referenced to measure pile shaft capacity shows acceptable accuracy of the developed model.