Prediction of Ultimate Bearing Capacity of Pile Foundation Based on Machine Learning System Using Matlab
Year: 2025
Type: article
Abstract: The prediction of ultimate bearing capacity of pile foundations plays a crucial role in the safe and cost-effective design of deep foundations.Traditional analytical and empirical approaches often fall short in addressing the complex, nonlinear interactions of soil-pile systems.In this study, a machine learning and deep learning-based system is developed using MATLAB to accurately predict the ultimate bearing capacity of piles.The model is trained and validated using a comprehensive dataset incorporating pile geometry, soil properties, and load test results.Various algorithms such as Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Deep Neural Networks (DNN) are implemented and compared for performance evaluation.The results demonstrate that deep learning models, particularly those using multilayer perceptron's and optimized hyperparameters, provide superior prediction accuracy over traditional methods.This approach offers a reliable alternative for geotechnical engineers to assess pile capacity efficiently, minimizing the need for costly and time-consuming field testing.
Language: English
Subfield: Civil and Structural Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4413368500