eprintid: 1334
rev_number: 7
eprint_status: archive
userid: 7
dir: disk0/00/00/13/34
datestamp: 2025-02-08 05:36:59
lastmod: 2025-02-08 05:36:59
status_changed: 2025-02-08 05:36:59
type: article
metadata_visibility: show
creators_name: Palalane, Lesego
creators_name: Dithinde, Mahongo
title: The Use of Machine Learning Approach to Predict Pile Capacity in Non-Cohesive Soils
ispublished: pub
subjects: TA
divisions: j6
full_text_status: public
keywords: Machine learning, SPT-based pile methods, Load Bearing Capacity, Full-scale Load Test, Chin extrapolation method, Terzhagi’s 10% criteria.
abstract: Existing theoretical and empirical pile design methods cannot accurately model the complex interaction between piles and soil. Consequently, there is a growing trend towards utilizing machine learning techniques to better capture the nonlinear soil-pile interaction. This paper aims to predict the capacity of bored piles in cohesionless soils using a machine learning approach. The machine learning algorithm was trained using a database of 18 bored pile cases in non-cohesive soils and validated with a separate dataset of 8 bored piles in cohesionless soil. Moreover, the performance of the machine learning method was compared with that of a traditional pile design method (i.e., SA-SPT method) in Southern Africa. The evaluation was based on the ratio of measured capacity to predicted capacity (Qm/Qp) statistics and the coefficient of determination (R2). The results showed an R2 of 0.89 for the machine learning method compared to 0.85 for the SA-SPT method, indicating the superior accuracy of the machine learning approach in predicting pile capacity.
date: 2024-09-15
publication: Journal of Civil Engineering and Urbanism
volume: 14
number: 3s
publisher: Scienceline Publication, Ltd
pagerange: 311-317
id_number: doi:10.54203/jceu.2024.34
refereed: TRUE
issn: 22520430
official_url: https://doi.org/10.54203/jceu.2024.34
j_index: notindex
citation:    (2024)     The Use of Machine Learning Approach to Predict Pile Capacity in Non-Cohesive Soils.   Journal of Civil Engineering and Urbanism.  pp. 311-317.  ISSN 22520430   
document_url: http://eprints.science-line.com/id/eprint/1334/1/JCEU14%283s%29311-317%2C2024.pdf