Predicting resilient modulus of flexible pavement foundation using extreme gradient boosting based optimised models: Fid-Bau Portal

Fachinformationsdienst BAUdigital

A platform for research: civil engineering, architecture and urbanism

Predicting resilient modulus of flexible pavement foundation using extreme gradient boosting based optimised models

Sarkhani Benemaran, Reza / Esmaeili-Falak, Mahzad / Javadi, Akbar

Resilient modulus ( $M_R$ $M_{R}$ ) plays the most critical role in the evaluation and design of flexible pavement foundations. $M_R$ $M_{R}$ is utilised as the principal parameter for representing stiffness and behaviour of flexible pavement foundation in experimental and semi-empirical approaches. To determine $M_R$ $M_{R}$ , cyclic triaxial compressive experiments under different confining pressures and deviatoric stresses are needed. However, such experiments are costly and time-consuming. In the present study, an extreme gradient boosting-based ( $XGB$ $X G B$ ) model is presented for predicting the resilient modulus of flexible pavement foundations. The model is optimised using four different optimisation methods (particle swarm optimisation ( $PSO$ $P S O$ ), social spider optimisation ( $SSO$ $S S O$ ), sine cosine algorithm ( $SCA$ $S C A$ ), and multi-verse optimisation ( $MVO$ $M V O$ )) and a database collected from previously published technical literature. The outcomes present that all developed designs have good workability in estimating the $M_R$ $M_{R}$ of flexible pavement foundation, but the $PSO-XGB$ $P S O - X G B$ models have the best prediction accuracy considering both training and testing datasets.

Access

Check availability in my library

Order at Subito €

Page navigation

Document information

Export, share and cite

Predicting resilient modulus of flexible pavement foundation using extreme gradient boosting based optimised models

Sarkhani Benemaran, Reza / Esmaeili-Falak, Mahzad / Javadi, Akbar

Resilient modulus ( $M_R$ $M_{R}$ ) plays the most critical role in the evaluation and design of flexible pavement foundations. $M_R$ $M_{R}$ is utilised as the principal parameter for representing stiffness and behaviour of flexible pavement foundation in experimental and semi-empirical approaches. To determine $M_R$ $M_{R}$ , cyclic triaxial compressive experiments under different confining pressures and deviatoric stresses are needed. However, such experiments are costly and time-consuming. In the present study, an extreme gradient boosting-based ( $XGB$ $X G B$ ) model is presented for predicting the resilient modulus of flexible pavement foundations. The model is optimised using four different optimisation methods (particle swarm optimisation ( $PSO$ $P S O$ ), social spider optimisation ( $SSO$ $S S O$ ), sine cosine algorithm ( $SCA$ $S C A$ ), and multi-verse optimisation ( $MVO$ $M V O$ )) and a database collected from previously published technical literature. The outcomes present that all developed designs have good workability in estimating the $M_R$ $M_{R}$ of flexible pavement foundation, but the $PSO-XGB$ $P S O - X G B$ models have the best prediction accuracy considering both training and testing datasets.

Predicting resilient modulus of flexible pavement foundation using extreme gradient boosting based optimised models

Sarkhani Benemaran, Reza / Esmaeili-Falak, Mahzad / Javadi, Akbar

Resilient modulus ( $M_R$ $M_{R}$ ) plays the most critical role in the evaluation and design of flexible pavement foundations. $M_R$ $M_{R}$ is utilised as the principal parameter for representing stiffness and behaviour of flexible pavement foundation in experimental and semi-empirical approaches. To determine $M_R$ $M_{R}$ , cyclic triaxial compressive experiments under different confining pressures and deviatoric stresses are needed. However, such experiments are costly and time-consuming. In the present study, an extreme gradient boosting-based ( $XGB$ $X G B$ ) model is presented for predicting the resilient modulus of flexible pavement foundations. The model is optimised using four different optimisation methods (particle swarm optimisation ( $PSO$ $P S O$ ), social spider optimisation ( $SSO$ $S S O$ ), sine cosine algorithm ( $SCA$ $S C A$ ), and multi-verse optimisation ( $MVO$ $M V O$ )) and a database collected from previously published technical literature. The outcomes present that all developed designs have good workability in estimating the $M_R$ $M_{R}$ of flexible pavement foundation, but the $PSO-XGB$ $P S O - X G B$ models have the best prediction accuracy considering both training and testing datasets.

Access

Check availability in my library

Order at Subito €

Page navigation

Document information

Export, share and cite

Document information

Title:

Predicting resilient modulus of flexible pavement foundation using extreme gradient boosting based optimised models

Contributors:

Sarkhani Benemaran, Reza (author) / Esmaeili-Falak, Mahzad (author) / Javadi, Akbar (author)

Published in:

International Journal of Pavement Engineering ; 24

Publication date:

2023-01-28

ISSN:

1029-8436 , 1477-268X

DOI:

https://doi.org/10.1080/10298436.2022.2095385

Type of media:

Article (Journal)

Type of material:

Electronic Resource

Language:

English

Keywords:

Resilient modulus prediction , artificial neural networks , extreme gradient boosting , PSO , MVO , SSO , SCA

Similar titles

Composite Resilient Modulus of Geogrid Stabilized Pavement Foundation

Tamrakar, Prajwol / Wayne, Mark H. | ASCE | 2023

Composite Resilient Modulus of Geogrid Stabilized Pavement Foundation

Tamrakar, Prajwol / Wayne, Mark H. | British Library Conference Proceedings | 2023

Soil-Property-Based Subgrade Resilient Modulus Estimation for Flexible Pavement Design

Hall, K. D. / Thompson, M. R. | British Library Online Contents | 1994

Use of Resilient Modulus Test Results in Flexible Pavement Design

Nazarian, S. / Abdallah, I. / Meshkani, A. et al. | British Library Conference Proceedings | 2003

Resilient Modulus-Pavement Subgrade Design Value

Boudreau, R. L. | British Library Conference Proceedings | 2003