Development of pile bearing capacity prediction model based on O-cell test data using ANN machine learning

Abstract

Accurately predicting the bearing capacity of piles is a significant challenge in geotechnical engineering, especially considering the complex interactions between soil and piles. This study aims to develop a machine learning-based model to estimate the bearing capacity of piles using experimental data obtained from O-cell load tests. The dataset includes detailed information on pile geometry, material properties, soil characteristics, and measured bearing capacities. Advanced machine learning techniques, specifically Artificial Neural Networks (ANN), were applied to capture the nonlinear relationships between input parameters and pile bearing capacity. The findings confirm the potential of machine learning models to enhance the reliability and efficiency of pile design processes. This study not only provides a robust predictive tool but also contributes to promoting data-driven approaches in geotechnical engineering practice.

Keyword: Pile Load-Bearing Capacity, O-cell test, Machine learning, Static Pile Load Test.