Development of a constitutive model for evaluation of bearing capacity from CPT and theoretical analysis using ann techniques

Abstract

Bearing capacity is significant value in pile design. Various approaches have been introduced to estimate the axial pile capacity. These approaches have restrictions and accordingly did not implement uniform and precise estimation of axial pile capacity. To add a value of the effort to achieve a proper and accurate relationship of a cone penetration test, including axial pile capacity, the Artificial Neural Networks (ANN) method is employed in this paper, which can be applied in cases where the relationship between the input parameters is unknown. In this paper, ANN was used to predict the bearing capacity of bored and driven piles. The present study uses the neural network approach to develop a model that can be adopted to predict bearing capacity values using ANN Techniques and can comfortably accommodate new data as this becomes available. ANN was used to predict the bearing capacity of bored and driven piles. The data, which is used as inputs accompanied by CPT. Furthermore, three artificial neural network models were generated. All models show that ANN provides a more accurate result by comparing it with the available CPT method.