Estimation of load-bearing capacity of bored piles using machine learning models

The load-bearing capacity of bored piles is an essential parameter in the foundation design of a structure. In the present study, thee Machine Learning (ML) methods, namely Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Machine (SVM), and Artificial Neural Network (ANN), were utilized to estimate the load-bearing capacity of bored piles based on limited engineering parameters of pile and soil obtained from 75 test sites in Vietnam. These parameters include pile diameter, pile length, the tensile strength of the main longitudinal steel bar, compressive strength of concrete, average SPT index at the tip of the pile, and average SPT index at the pile body. Validation of the methods was verified using standard statistical metrics, namely Root Mean Square Error (RMSE) and Correlation coefficient (R). The results show that all the proposed models have a good potential in predicting correctly the load-bearing capacity of bored piles on training data (R>0.93) and on testing data (R>0.88). Still, the performance of the SVM model is the best (R=0.985 for training and R=0.958 for testing). Thus, the SVM model can accurately predict the load-bearing capacity of bored piles for properly designing the civil engineering structure foundation.