Load–settlement modeling of axially loaded steel driven piles using CPT-based recurrent neural networks

The design of pile foundations requires good estimations of the pile load-carrying capacity and the settlement. Designs for bearing capacity and settlement have been traditionally carried out separately. However, soil resistance and settlement are influenced by each other, and thus, the design of pile foundations should consider the bearing capacity and the settlement together. This requires that the full load–settlement response of the piles be accurately predicted. However, it is well known that the actual load–settlement response of pile foundations can only be obtained through load tests carried out in-situ, which are expensive and time-consuming. In this technical note, recurrent neural networks (RNNs) were used to develop a prediction model that can resemble the load–settlement response of steel driven piles subjected to axial loading. The developed RNN model was calibrated and validated using several in-situ full-scale pile load tests, as well as cone penetration test (CPT) data. The results indicate that the developed RNN model has the ability to reliably predict the load–settlement response of axially loaded steel driven piles, and thus, can be used by geotechnical engineers for routine design practice.