Showing papers by "Pijush Samui published in 2010"

Prediction of swelling pressure of soil using artificial intelligence techniques

Abstract: The swelling pressure of soil depends upon various soil parameters such as mineralogy, clay content, Atterberg's limits, dry density, moisture content, initial degree of saturation, etc. along with structural and environmental factors. It is very difficult to model and analyze swelling pressure effectively taking all the above aspects into consideration. Various statistical/empirical methods have been attempted to predict the swelling pressure based on index properties of soil. In this paper, the computational intelligence techniques artificial neural network and support vector machine have been used to develop models based on the set of available experimental results to predict swelling pressure from the inputs; natural moisture content, dry density, liquid limit, plasticity index, and clay fraction. The generalization of the model to new set of data other than the training set of data is discussed which is required for successful application of a model. A detailed study of the relative performance of the computational intelligence techniques has been carried out based on different statistical performance criteria.

Site Characterization Model Using Artificial Neural Network and Kriging

Abstract: In this paper, the problem of site characterization is treated as a task of function approximation of the large existing data from standard penetration tests (SPTs) in three-dimensional subsurface of Bangalore, India. More than 2,700 field SPT values (N) has been collected from 766 boreholes spread over an area of 220 -km2 area in Bangalore, India. To get N corrected value ( Nc ) , N values have been corrected for different parameters such as overburden stress, size of borehole, type of sampler, length of connected rod. In three-dimensional analysis, the function Nc = Nc ( X,Y,Z ) , where X , Y , and Z are the coordinates of a point corresponds to Nc value, is to be approximated with which Nc value at any half-space point in Bangalore, India can be determined. An attempt has been made to develop artificial neural network (ANN) model using multilayer perceptrons that are trained with Levenberg-Marquardt back-propagation algorithm. Also, a geostatistical model based on ordinary kriging technique has been ad...

Correlation between SPT, CPT and MASW

Abstract: Geotechnical engineers use in situ tests for site characterization. In this paper, an attempt has also been made to evaluate geotechnical site characterization by carrying out in situ tests using different in situ techniques such as standard penetration test (SPT), cone penetration tests(CPT) and multi channel analysis of surface wave (MASW) techniques. For this purpose a typical site was selected wherein a man made homogeneous embankment and as well natural ground has been met. For this typical site, in situ tests (SPT, CPT and MASW) have been carried out in different ground conditions and the obtained test results are compared. Three CPT continuous test profiles, fifty-four SPT tests and nine MASW test profiles with depth have been carried out for the selected site covering both homogeneous embankment and natural ground. Relationships have been developed between V s , ( N 1 )60 and q c values for this specific site.

Spatial variability of SPT data using ordinary and disjunctive kriging

Abstract: The purpose of this study is to develop a geostastistical model based on ordinary and disjunctive kriging techniques to estimate spatial variability of SPT (N) data in the three-dimensional subsurface of Bangalore. The database consists of 766 boreholes spread over a 220 sq km area, with several N values in each of them. The analysis has been done for corrected SPT (Nc) value. Ordinary kriging produces a linear estimator, whereas disjunctive kriging produces a nonlinear estimator. Knowledge of the semivariogram of the SPT data is used in the kriging theory to estimate the values at points in the subsurface of Bangalore where field measurements are not available. The capability of disjunctive kriging to be a nonlinear estimator and an estimator of conditional probability is explored. A cross-validation (Q1 and Q2) analysis is also done for the developed ordinary and disjunctive kriging models. For the data sets used in this study, disjunctive kriging has shown to be a better estimator than ordinary kriging...

Design of a piezovibrocone and calibration chamber

Abstract: This paper presents the details of indigenous development of the piezovibrocone and calibration chamber. The developed cone has a cylindrical friction sleeve of surface area, capped with a apex angle conical tip of cross sectional area. It has a hydraulic shaker, coupled to the cone penetrometer with a linear displacement unit. The hydraulic shaker can produce cyclic load in different types of wave forms (sine, Hover sine, triangular, rectangular and external wave) at a range of frequency 1-10 Hz with maximum amplitude of 10 cm. The piezovibrocone can be driven at the standard rate of 2 cm/sec using a loading unit of 10 ton capacity. The calibration chamber is of size . The sides of the chamber and the top as well as the bottom portions are rigid. It has a provision to apply confining pressure (to a maximum value of ) through the flexible rubber membrane inlined with the side walls of the calibration chamber. The preliminary static as well as dynamic cone penetration tests have been done sand in the calibration chamber. From the experimental results, an attempt has been made to classify the soil based on friction ratio () and the cone tip resistance ().

Applicability of Statistical Learning Algorithms for Spatial Variability of Rock Depth

Abstract: Two algorithms are outlined, each of which has interesting features for modeling of spatial variability of rock depth. In this paper, reduced level of rock at Bangalore, India, is arrived from the 652 boreholes data in the area covering 220 sq⋅km. Support vector machine (SVM) and relevance vector machine (RVM) have been utilized to predict the reduced level of rock in the subsurface of Bangalore and to study the spatial variability of the rock depth. The support vector machine (SVM) that is firmly based on the theory of statistical learning theory uses regression technique by introducing e-insensitive loss function has been adopted. RVM is a probabilistic model similar to the widespread SVM, but where the training takes place in a Bayesian framework. Prediction results show the ability of learning machine to build accurate models for spatial variability of rock depth with strong predictive capabilities. The paper also highlights the capability of RVM over the SVM model.

Relevance Vector Machine for Evaluating Seismic Liquefaction Potential Using Shear Wave Velocity

Abstract: The use of the shear wave velocity data as a field index for evaluating the liquefaction potential of sands is receiving increased attention because both shear wave velocity and liquefaction resistance are similarly influenced by many of the same factors such as void ratio, state of stress, stress history and geologic age. In this paper, the potential of support vector machine (SVM) based classification approach has been used to assess the liquefaction potential from actual shear wave velocity data. In this approach, an approximate implementation of a structural risk minimization (SRM) induction principle is done, which aims at minimizing a bound on the generalization error of a model rather than minimizing only the mean square error over the data set. Here SVM has been used as a classification tool to predict liquefaction potential of a soil based on shear wave velocity. The dataset consists the information of soil characteristics such as effective vertical stress (sigma'(v0)), soil type, shear wave velocity (V-s) and earthquake parameters such as peak horizontal acceleration (a(max)) and earthquake magnitude (M). Out of the available 186 datasets, 130 are considered for training and remaining 56 are used for testing the model. The study indicated that SVM can successfully model the complex relationship between seismic parameters, soil parameters and the liquefaction potential. In the model based on soil characteristics, the input parameters used are sigma'(v0), soil type. V-s, a(max) and M. In the other model based on shear wave velocity alone uses V-s, a(max) and M as input parameters. In this paper, it has been demonstrated that Vs alone can be used to predict the liquefaction potential of a soil using a support vector machine model. (C) 2010 Elsevier B.V. All rights reserved.

Determination of stability numbers for soil slopes following non-associated non-coaxial flow rule

Abstract: The assumption of an associated flow rule overestimates the volume increase during shear than that is observed for most of the soils and also for an associated flow rule the stresses acting over various rupture surfaces do not appear in the energy rate expressions. For a non-associated non-coaxial flow rule it is essential to define the stresses along the rupture surface to find the rate of dissipation of internal energy. In the present work, stability number for the homogeneous soil slope obeying non-associated non-coaxial flow rule has been determined by defining the stresses along the rupture surface using the assumption of interslice forces as earlier introduced by Fellenius (1936) and Bishop (1955). In the analysis, effects of seismic force have been also incorporated. Optimization methods and neural network have been implemented to obtain the stability numbers. The result indicates that the effect of dilatancy angle (ψ) on the results was seen to be less significant for non-coaxial flow rule...