0
  • DE
  • EN
  • FR
  • Base de données et galerie internationale d'ouvrages d'art et du génie civil

Publicité

Prediction of California Bearing Ratio of Granular Soil by Multivariate Regression and Gene Expression Programming

Auteur(s): ORCID
ORCID
ORCID
Médium: article de revue
Langue(s): anglais
Publié dans: Advances in Civil Engineering, , v. 2022
Page(s): 1-16
DOI: 10.1155/2022/7426962
Abstrait:

This research demonstrates the results of an investigation into the California bearing ratio (CBR) of granular soils from Qassim region, Saudi Arabia, using multilinear regression (MLR), pure quadratic (PQ) models, and gene expression programming (GEP) methods utilized to develop mathematical models for estimating the CBR based on basic soil index properties. In this study, samples were collected from different borrowing pits in the Qassim area. Forty-three samples of soil were taken and transferred to a laboratory for examination. Seven multilinear regressions and seven PQ models were investigated, while four GEP models were made. The selection of each model variable depends on soil indices, grouping into grain size distribution, Atterberg limits, and compaction parameters. The results of this analysis showed that the PQ model had a higher accuracy [coefficient of determination (R2) = 0.89, root mean square error (RMSE) = 16.006, uncertainty (U95) = 16.17, and reliability = 57%] than the multilinear regression model, which has a lower accuracy model [R2 = 0.811, RMSE = 20.791, U95 = 15.569, and reliability = 51%]. The best GEP model yields [R2 = 0.776, RMSE = 22.552, U95 = 15.787, and reliability = 53%]. Furthermore, sensitivity analysis was conducted to distinguish the influences of different input variables on CBR; it was found that fines percentage (F200), maximum dry density (MDD), and optimum moisture content (OMC) are the most influential variables.

Copyright: © Mudthir Bakri et al. et al.
License:

Cette oeuvre a été publiée sous la license Creative Commons Attribution 4.0 (CC-BY 4.0). Il est autorisé de partager et adapter l'oeuvre tant que l'auteur est crédité et la license est indiquée (avec le lien ci-dessus). Vous devez aussi indiquer si des changements on été fait vis-à-vis de l'original.

  • Informations
    sur cette fiche
  • Reference-ID
    10691829
  • Publié(e) le:
    23.09.2022
  • Modifié(e) le:
    10.11.2022
 
Structurae coopère avec
International Association for Bridge and Structural Engineering (IABSE)
e-mosty Magazine
e-BrIM Magazine