We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
New Model to Predict Bearing Capacity of Shallow Foundations Resting on Cohesionless Soil.
- Authors
Alzabeebee, Saif; Alshkane, Younis M. A.; Keawsawasvong, Suraparb
- Abstract
Predicting the bearing capacity is one of the tasks that geotechnical engineers do on a daily basis, yet the accuracy of the available methods needs to be further improved. This paper proposes a new model to accurately predict the bearing capacity of foundations resting on cohesionless soil. The new model has been proposed using a data-driven method called multi-objective genetic algorithm evolutionary computing analysis. The database used in the model development has been collected from previous studies, and part of this database has been used to test the model to check its accuracy using data that did not influence the model training. The accuracy of the model has been assessed using mean absolute error (MAE), root mean square error (RMSE), mean, a20-index, and coefficient of determination (R2). The new model scored MAE, RMSE, mean, a20-index, and R2 of 65 kPa, 99 kPa, 0.99, 0.68, and 0.97, respectively, for the training data and 58 kPa, 122 kPa, 0.99, 0.63, and 0.97, respectively, for the testing data. The accuracy of the new model has also been compared with the classical bearing capacity equations of Terzaghi, Vesic, and Hansen and with other data-driven models, where it was found that the accuracy of the new model is better as it scored better statistical indicators and also scored better in the error level-cumulative frequency relationship. Thus, the new model can optimize future designs, as its accuracy has been demonstrated. Also, this model can be further improved in the future when new data becomes available.
- Subjects
BEARING capacity of soils; SHALLOW foundations; STANDARD deviations; DATABASES; GENETIC algorithms; EVOLUTIONARY algorithms
- Publication
Geotechnical & Geological Engineering, 2023, Vol 41, Issue 6, p3531
- ISSN
0960-3182
- Publication type
Article
- DOI
10.1007/s10706-023-02472-y