Search

In recent years, the use of helical piles as a deep foundation option for structures has increased dramatically because they offer definite advantages over other solutions. The present study undertook a comprehensive investigation of the axial compressive behavior of helical piles in both sandy and clayey types of soil using finite element (FE) modeling. Since the helices of helical piles are more likely to disturb the soil adjacent to the pile, first some approaches are proposed to consider the effect of soil disturbance during a helical pile installation in numerical models. The numerical models have been validated and calibrated through full-scale compressive loading results using the ABAQUS software. The validated numerical models were used to investigate the load transfer mechanism of a typical helical pile in different types of sandy and clayey soil, and the numerically obtained ultimate bearing capacities were compared with the theoretical ones. Based on the comparison, it was found that the theoretical procedure overpredicts the ultimate capacity of helical piles in medium and dense sand. Additionally, different geometrical aspects of a typical helical pile were investigated using FE modeling in order to employ perfect geometry for studying the compressive behavior of a helical pile group with a square grid arrangement. The results revealed that the shape of the block failure mechanism in clayey soil differs from that in sandy soil. The acquired shapes are used to suggest a theoretical method for calculating the ultimate bearing capacity of a helical pile group based on the block failure mechanism. [ABSTRACT FROM AUTHOR]

A new forecast method is proposed in order to improve the estimation accuracy of the ultimate bearing capacity (UBC) of single driven piles. The performance of the adaptive neuro-fuzzy inference system (ANFIS) and multilayer perceptron (MLP) models have been boosted using gray wolf optimization (GWO). To train the models, data were used from 100 driven piles in c-φ soil in different locations. The input parameters were pile area (m2), pile length (m), flap number, average cohesion (kN/m2) and friction angle (°), average soil specific weight (kN/m2) and average pile–soil friction angle (°), and the output was UBC. The results showed that both the MLP and ANFIS methods had good abilities to predict the UBC of the piles; however, the MLP-GWO model with a topology of 7 × 10 × 10 × 1 provided better results. The performance indices of this model were a RMSE of 1.86 kN and R2 of 0.991 for the test data. The validity of the MLP-GWO model was tested using a new experimental dataset, and the difference between actual and estimated UBC was very low (about 2%) and confirmed the high accuracy of the model. It was observed that the theoretical methods underestimated the UBC significantly, while the proposed model estimated the UBC with high accuracy. Sensitivity analysis confirmed that the pile area and length were the most effective factors for estimation of UBC. [ABSTRACT FROM AUTHOR]