Predicting the uplift capacity of circular anchors in frictional-cohesive soils using Kolmogorov-Arnold networks

Abstract This study investigates the uplift capacity of circular anchors embedded in frictional-cohesive soils under surcharge. The analysis focuses on three critical stability factors F c , F q , and F γ using Terzaghi’s principle of superposition to evaluate ultimate bearing capacity. These factor...

Full description

Saved in:
Bibliographic Details
Main Authors: Tran Vu-Hoang, Tan Nguyen, Jim Shiau, Hung-Thinh Pham-Tran, Trung Nguyen-Thoi
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-98945-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713098715299840
author Tran Vu-Hoang
Tan Nguyen
Jim Shiau
Hung-Thinh Pham-Tran
Trung Nguyen-Thoi
author_facet Tran Vu-Hoang
Tan Nguyen
Jim Shiau
Hung-Thinh Pham-Tran
Trung Nguyen-Thoi
author_sort Tran Vu-Hoang
collection DOAJ
description Abstract This study investigates the uplift capacity of circular anchors embedded in frictional-cohesive soils under surcharge. The analysis focuses on three critical stability factors F c , F q , and F γ using Terzaghi’s principle of superposition to evaluate ultimate bearing capacity. These factors are influenced by the soil’s internal friction angle, the geometric ratio of anchor depth to diameter, and the interface roughness between the anchor and soil. Three predictive models for these stability factors are developed using advanced computational methods, including finite element limit analysis (FELA) with adaptive meshing and Kolmogorov-Arnold Networks (KAN). This research is the first to apply KAN in anchor behavior studies, demonstrating its enhanced ability to model complex data relationships compared to artificial neural networks (ANN). Additionally, a closed-form solution for stability factors is derived through KAN, providing an efficient method for predicting bearing capacity. The optimized models exhibit high coefficient of determination (R²) values and low root mean square errors (RMSE) for training and testing datasets. Sensitivity analysis validates the robustness of the proposed models. These findings advance the understanding of circular anchors’ bearing capacity in frictional-cohesive soils, offering practical design insights for various soil conditions.
format Article
id doaj-art-ca7102fb5b8e4f8ba0d891fe9f939660
institution DOAJ
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ca7102fb5b8e4f8ba0d891fe9f9396602025-08-20T03:14:03ZengNature PortfolioScientific Reports2045-23222025-04-0115112610.1038/s41598-025-98945-6Predicting the uplift capacity of circular anchors in frictional-cohesive soils using Kolmogorov-Arnold networksTran Vu-Hoang0Tan Nguyen1Jim Shiau2Hung-Thinh Pham-Tran3Trung Nguyen-Thoi4Faculty of Civil Engineering, Ton Duc Thang UniversitySmart Computing in Civil Engineering Research Group, Faculty of Civil Engineering, Ton Duc Thang UniversitySchool of Engineering, University of Southern QueenslandFaculty of Civil Engineering, Ton Duc Thang UniversityLaboratory for Applied and Industrial Mathematics, Institute for Computational Science and Artificial Intelligence, Van Lang UniversityAbstract This study investigates the uplift capacity of circular anchors embedded in frictional-cohesive soils under surcharge. The analysis focuses on three critical stability factors F c , F q , and F γ using Terzaghi’s principle of superposition to evaluate ultimate bearing capacity. These factors are influenced by the soil’s internal friction angle, the geometric ratio of anchor depth to diameter, and the interface roughness between the anchor and soil. Three predictive models for these stability factors are developed using advanced computational methods, including finite element limit analysis (FELA) with adaptive meshing and Kolmogorov-Arnold Networks (KAN). This research is the first to apply KAN in anchor behavior studies, demonstrating its enhanced ability to model complex data relationships compared to artificial neural networks (ANN). Additionally, a closed-form solution for stability factors is derived through KAN, providing an efficient method for predicting bearing capacity. The optimized models exhibit high coefficient of determination (R²) values and low root mean square errors (RMSE) for training and testing datasets. Sensitivity analysis validates the robustness of the proposed models. These findings advance the understanding of circular anchors’ bearing capacity in frictional-cohesive soils, offering practical design insights for various soil conditions.https://doi.org/10.1038/s41598-025-98945-6Uplift capacityFrictional-cohesive soilsTerzaghi stability factorsKolmogorov-Arnold networks (KAN)Closed-form solutionSensitivity analysis
spellingShingle Tran Vu-Hoang
Tan Nguyen
Jim Shiau
Hung-Thinh Pham-Tran
Trung Nguyen-Thoi
Predicting the uplift capacity of circular anchors in frictional-cohesive soils using Kolmogorov-Arnold networks
Scientific Reports
Uplift capacity
Frictional-cohesive soils
Terzaghi stability factors
Kolmogorov-Arnold networks (KAN)
Closed-form solution
Sensitivity analysis
title Predicting the uplift capacity of circular anchors in frictional-cohesive soils using Kolmogorov-Arnold networks
title_full Predicting the uplift capacity of circular anchors in frictional-cohesive soils using Kolmogorov-Arnold networks
title_fullStr Predicting the uplift capacity of circular anchors in frictional-cohesive soils using Kolmogorov-Arnold networks
title_full_unstemmed Predicting the uplift capacity of circular anchors in frictional-cohesive soils using Kolmogorov-Arnold networks
title_short Predicting the uplift capacity of circular anchors in frictional-cohesive soils using Kolmogorov-Arnold networks
title_sort predicting the uplift capacity of circular anchors in frictional cohesive soils using kolmogorov arnold networks
topic Uplift capacity
Frictional-cohesive soils
Terzaghi stability factors
Kolmogorov-Arnold networks (KAN)
Closed-form solution
Sensitivity analysis
url https://doi.org/10.1038/s41598-025-98945-6
work_keys_str_mv AT tranvuhoang predictingtheupliftcapacityofcircularanchorsinfrictionalcohesivesoilsusingkolmogorovarnoldnetworks
AT tannguyen predictingtheupliftcapacityofcircularanchorsinfrictionalcohesivesoilsusingkolmogorovarnoldnetworks
AT jimshiau predictingtheupliftcapacityofcircularanchorsinfrictionalcohesivesoilsusingkolmogorovarnoldnetworks
AT hungthinhphamtran predictingtheupliftcapacityofcircularanchorsinfrictionalcohesivesoilsusingkolmogorovarnoldnetworks
AT trungnguyenthoi predictingtheupliftcapacityofcircularanchorsinfrictionalcohesivesoilsusingkolmogorovarnoldnetworks