Journal
GEOTECHNICAL AND GEOLOGICAL ENGINEERING
Volume 37, Issue 5, Pages 4643-4647Publisher
SPRINGER
DOI: 10.1007/s10706-019-00928-8
Keywords
Minimax Probability Machine Regression; Gaussian Process Regression; Variance; Artificial Neural Network; Pile foundation; Clay; Friction capacity
Categories
Ask authors/readers for more resources
Friction capacity (f(s)) of driven pile in clay is key parameter for designing pile foundation. This study employs Gaussian Process Regression (GPR), and Minimax Probability Machine Regression (MPMR) for determination of f(s) of driven piles in clay. GPR is a Bayesian nonparametric regression model. MPMR is a probabilistic model. Pile length (L), pile diameter (D), effective vertical stress (sigma'(v)), undrained shear strength (S-u) have been used as input variables of GPR and MPMR. The output of the models is f(s). The developed GPR, MPMR models have been compared with the Artificial Neural Network (ANN). GPR also gives the variance of predicted f(s). The results prove that the developed GPR and MPMR are efficient models for prediction of f(s) of driven piles in clay.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available