A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Prediction of Bearing Capacity of Geogrid-Reinforced Stone Columns Using Support Vector Regression
The prediction of the bearing capacity (qrs) of unreinforced sand bed and geogrid-reinforced sand bed resting over a group of stone columns floating in soft clay is an important task due to the complex geometry and uncertainty involved in the different geotechnical parameters. Moreover, there is no established bearing capacity equation available on this topic. Because of the complex, elaborate, and expensive estimation of qrs, it is required to develop a precise prediction model, which is supposed to be nonlinear. In this study, the potential of the support vector regression (SVR) technique for qrs prediction is investigated. The performance of the SVR model with three different kernel functions is examined. The prediction performance of the SVR model with exponential radial basis kernel (ERBF) is compared with the artificial neural network (ANN) model. A sensitivity analysis is also performed to demonstrate the effectiveness of each input variable on qrs. Finally, using the SVR-ERBF model an empirical equation is proposed to predict tqrs for practical application purposes. Obtained results approve the robustness of the SVR-ERBF model for indirect prediction of qrs.
Prediction of Bearing Capacity of Geogrid-Reinforced Stone Columns Using Support Vector Regression
The prediction of the bearing capacity (qrs) of unreinforced sand bed and geogrid-reinforced sand bed resting over a group of stone columns floating in soft clay is an important task due to the complex geometry and uncertainty involved in the different geotechnical parameters. Moreover, there is no established bearing capacity equation available on this topic. Because of the complex, elaborate, and expensive estimation of qrs, it is required to develop a precise prediction model, which is supposed to be nonlinear. In this study, the potential of the support vector regression (SVR) technique for qrs prediction is investigated. The performance of the SVR model with three different kernel functions is examined. The prediction performance of the SVR model with exponential radial basis kernel (ERBF) is compared with the artificial neural network (ANN) model. A sensitivity analysis is also performed to demonstrate the effectiveness of each input variable on qrs. Finally, using the SVR-ERBF model an empirical equation is proposed to predict tqrs for practical application purposes. Obtained results approve the robustness of the SVR-ERBF model for indirect prediction of qrs.
Prediction of Bearing Capacity of Geogrid-Reinforced Stone Columns Using Support Vector Regression
Debnath, P. (author) / Dey, A. K. (author)
2017-12-05
Article (Journal)
Electronic Resource
Unknown
Geogrid coated vibro stone columns
| British Library Conference Proceedings | 2004
Bearing Capacity of Geogrid Reinforced Grounds
| British Library Conference Proceedings | 1994