Determination of footing bearing capacity on reinforced sand layer by svm and rbf kernel

Determination of footing bearing capacity on reinforced sand layer by svm and rbf kernel

behnaz jahani1 ali heidaripanah2 fazlollah soltani3 amin baghizadeh4

1) Geotechnical Department of Graduate University of Advanced Technology, Kerman, Iran
2) Department of research Center of road and Urban Development , tehran, Iran
3) Geotechnical Department of Graduate University of Advanced Technology, Kerman, Iran
4) Geotechnical Department of Graduate University of Advanced Technology, Kerman, Iran

IOI Code : XYEA-BZCHE
Publication : The 4th International Congress On Civil Engineering, Architecture & Urban Development(4icsau.ir)
Abstract :
    Reinforced soil foundations have been employed in engineering practice to increase the soil bearing capacity and to reduce the potential footing settlement (4). Bearing capacity tests were carried out on two layered soil. The top layer of soil was well graded soil compacted at higher densities (16.24, 16.44, 16.55 and 16.76 kN/m3) and the lower layer was of poorly graded sand compacted at low densities (15.05, 15.15, 15.25 and 15.58 kN/m3). Due to time-consuming and equipment requirements for conducting the bearing capacity test, it appears to be demanded to develop the numerical models in order to predict the bearing capacity of strip footing. .The support vector machine (SVM) is an emerging machine learning technique where prediction error and model complexity are simultaneously minimized. This paper examines the potential of SVM to predict the bearing capacity of strip footing on reinforced layer. This SVM is firmly based on the statistical learning theory and uses the regression technique by introducing accuracy (ε) insensitive loss function. radial basis kernel functions (RBF) with their estimated optimum parameter was applied for the classification of the data sets and the results were analyzed thoroughly. Results showed that SVMs, especially with the use of radial basis function kernel, outperform the maximum likelihood classifier in terms of overall and individual class accuracies (2). In order to create the model and to validate the algorithm performance, about 80% of data were randomly selected as the training data set and the remaining ones applied as the testing data set. A sensitivity analysis has been also performed to investigate the importance of the input parameters. The study shows that SVM has the potential to be a useful and practical tool for prediction of bearing capacity of strip footing on reinforced layer

Keywords : strip footing reinforced soil svm rbf kernel