OCR Prediction Using Support Vector Machine Based on Piezocone Data

The determination of the overconsolidation ratio (OCR) of clay deposits is an important task in geotechnical engineering practice. This paper examines the potential of a support vector machine (SVM) for predicting the OCR of clays from piezocone penetration test data. SVM is a statistical learning theory based on a structural risk minimization principle that minimizes both error and weight terms. The five input variables used for the SVM model for prediction of OCR are the corrected cone resistance (qt), vertical total stress (sigmav), hydrostatic pore pressure (u0), pore pressure at the cone tip (u1), and the pore pressure just above the cone base (u2). Sensitivity analysis has been performed to investigate the relative importance of each of the input parameters. From the sensitivity analysis, it is clear that qt=primary in situ data influenced by OCR followed by sigmav, u0, u2, and u1. Comparison between SVM and some of the traditional interpretation methods is also presented. The results of this study have shown that the SVM approach has the potential to be a practical tool for determination of OCR.

Impact resistance and evaluation of retained strength on geotextiles

Over the last few decades, geotextiles have progressively been incorporated into geotechnical applications, especially in the field of coastal engineering. Geotextile materials often act as separator and a filter layer between rocks laid above and subgrade beneath. This versatile material has gradually substituted traditional granular materials because of its ease of installation, consistent quality and labour costefficiency. However, geotextiles often suffer damage during installation due to high dynamic bulk loading of rock placement. This can degrade geotextiles' mechanical strength. The properties considered in this paper include the impact resistance and retained strength of geotextiles. In general, the greater the impact energy applied to geotextiles, the greater the potential for damage. Results highlight the inadequacy of using index derived values as an indicator to determine geotextile performance on site because test results shows that geotextiles (staple fibre (SF) and continuous filament (CF)) with better mechanical properties did not outperform lower mechanical strength materials. The toughest CF product with a CBR index value of 9696N shows inferior impact resistance compared to SF product with the least CBR strength (2719N) given the same impact energy of 9.02 kJ. Test results also indicated that the reduction of strength for CF materials were much greater (between 20 and 50%) compared to SF materials (between 0 and 5%) when subjected to the same impact energy of 4.52 kJ.

Field performance of in-service cast iron gas reticulation pipe buried in reactive clay

Field instrumentation of an in-service cast iron gas pipe buried in a residential area is detailed in this paper. The aim of the study was to monitor the long-term pipe behavior to understand the mechanisms of pipe bending in relation to ground movement as a result of seasonal fluctuation of soil moisture content. Field data showed that variation of soil temperature, suction, and moisture content are closely related to the prevailing climate. Change of soil temperature is generally related to the ambient air temperature, with a variation of approximately −3°C −3°C per meter depth from the ground surface in summer (decrease with depth) and winter (increase with depth). Seasonal cyclic variation in moisture content was observed with maxima in February and March, and a minimum around September. The pipe top was under tensile strain during summer and subsequently subjected to compressive strain as soil swelling occurred as a result of increase in moisture content. The study suggests that downward pipe bending occurs in summer because of soil shrinkage, while upward pipe bending occurs in winter when the soil swells.

Support vector machine applied to settlement of shallow foundations on cohesionless soils

The determination of settlement of shallow foundations on cohesionless soil is an important task in geotechnical engineering. Available methods for the determination of settlement are not reliable. In this study, the support vector machine (SVM), a novel type of learning algorithm based on statistical theory, has been used to predict the settlement of shallow foundations on cohesionless soil. SVM uses a regression technique by introducing an ε – insensitive loss function. A thorough sensitive analysis has been made to ascertain which parameters are having maximum influence on settlement. The study shows that SVM has the potential to be a useful and practical tool for prediction of settlement of shallow foundation on cohesionless soil.

Analysis of shore line protection works in tsunami hit areas of east coast of India

Evaluation and design of shore protection works in the case of tsunamis assumes considerable importance in view of the impact it had in the recent tsunami of 26th December 2004 in India and other countries in Asia. The fact that there are no proper guidelines have made in the matters worse and resulted in the magnitude of damage that occurred. Survey of the damages indicated that the scour as a result of high velocities is one of the prime reasons for damages in the case of simple structures. It is revealed that sea walls in some cases have been helpful to minimize the damages. The objective of this paper is to suggest that design of shore line protection systems using expected wave heights that get generated and use of flexible systems such as geocells is likely to give a better protection. The protection systems can be designed to withstand the wave forces that corresponding to different probabilities of incidence. A design approach of geocells protection system is suggested and illustrated with reference to the data of wave heights in the east coast of India.

Site characterization model using least-square support vector machine and relevance vector machine based on corrected SPT data (N-c)

Statistical learning algorithms provide a viable framework for geotechnical engineering modeling. This paper describes two statistical learning algorithms applied for site characterization modeling based on standard penetration test (SPT) data. More than 2700 field SPT values (N) have been collected from 766 boreholes spread over an area of 220 sqkm area in Bangalore. To get N corrected value (N,), N values have been corrected (Ne) for different parameters such as overburden stress, size of borehole, type of sampler, length of connecting rod, etc. In three-dimensional site characterization model, the function N-c=N-c (X, Y, Z), where X, Y and Z are the coordinates of a point corresponding to N, value, is to be approximated in which N, value at any half-space point in Bangalore can be determined. The first algorithm uses least-square support vector machine (LSSVM), which is related to aridge regression type of support vector machine. The second algorithm uses relevance vector machine (RVM), which combines the strengths of kernel-based methods and Bayesian theory to establish the relationships between a set of input vectors and a desired output. The paper also presents the comparative study between the developed LSSVM and RVM model for site characterization. Copyright (C) 2009 John Wiley & Sons,Ltd.

Drained shear strength of fine-grained soil-solid surface interfaces

Herein are reported the results of an investigation on the effective angle of interfacial friction between fine-grained soils and solid surfaces as influenced by the roughness of the material surface, the soil type and the overconsolidation ratio. The ratio of interfacial friction angle to the angle of internal friction (evaluated at constant overconsolidation ratio) of the soil is independent of the overconsolidation ratio. An empirical correlation between this ratio and the roughness of the interface has been proposed.

A note on the choice of interfacial friction angle

Estimates of interfacial friction angle (delta) are necessary for the design of retaining structures and deep foundations, Recommendations in the literature regarding delta values are often contradictory and are therefore not easy to apply in geotechnical design, A critical examination of past studies in terms of data generation techniques used and conclusions drawn indicates that two distinctly different test procedures/techniques have been evolved. The interfacial situation in practice can also be categorized into two broad types, These two types of interface problems in geotechnical engineering are (a) the structure is placed on the free surface of prepared fill (type A situation) and (b) the fill is placed against the material surface which functions as a confined boundary (type B situation), The friction angle delta depends on the surface roughness of the construction material, But in the type A situation, it is independent of density and its limiting maximum value (delta(lim)) is the critical state friction angle phi(cv). In the type B situation, it is dependent on density of the fill and its limiting maximum value is the peak angle of internal friction phi(p) of the fill.

The log delta log t method for the determination of the coefficient of consolidation

The behaviour of saturated soils undergoing consolidation is very complex, It may not follow Terzaghi's theory over the entire consolidation process, Different soils may behave in such a way as to fit into Terzaghi's theory over some specific stages of the consolidation process (percentage of consolidation), This may be one of the reasons for the difficulties faced by the existing curve-fitting procedures in obtaining the coefficient of consolidation, c(v). It has been shown that the slope of the initial linear portion of the theoretical log U-log T curve is constant over a wider range of degree of consolidation, U, when compared with the other methods in use, This initial well-defined straight line in the log U-log T plot intersects the U = 100% line at T = pi/4, which corresponds to U = 88.3%, The proposed log delta-log t method is based on this observation, which gives the value of c(v) through simple graphical construction, In the proposed method, which is more versatile, identification of the characteristic straight lines is very clear; the intersection of these lines is more precise and the method does not depend upon the initial compression for the determination of c(v).

Secondary compression factor

When the variation of secondary compression, with log(10) t is non-linear, the quantification of secondary settlement through the coefficient of secondary compression, C-alpha epsilon, becomes difficult which frequently leads to an underestimate of the settlement, Log(10) delta - log(10) t representation of such true-compression data has the distinct advantage of exhibiting linear secondary compression behaviour over an appreciably larger time span. The slope of the secondary compression portion of the log(10) e - log(10) t curve expressed as Delta(log e)/(log t) and called the 'secondary compression factor', m, proves to be a better alternative to C-alpha epsilon and the prediction of secondary settlement is improved.

California bearing ratio behavior of cement-stabilized fly ash-soil mixes

Thermal power stations using pulverized coal as fuel generate large quantities of fly ash as a byproduct, which has created environmental and disposal problems. Using fly ash for gainful applications will solve these problems. Among the various possible uses for fly ash, the most massive and effective utilization is in geotechnical engineering applications like backfill material, construction of embankments, as a subbase material, etc. A proper understanding of fly ash-soil mixes is likely to provide viable solutions for its large-scale utilization. Earlier studies initiated in the laboratory have resulted in a good understanding of the California Bearing Ratio (CBR) behavior of fly ash-soil mixes. Subsequently, in order to increase the CBR value, cement has been tried as an additive to fly ash-soil mixes. This paper reports the results.

Mechanisms controlling the undrained strength behavior of remolded Ariake marine clays

The soft clay of Ariake Bay, in western Kyushu, Japan covers several hundred square kilometers. Ariake clay consists of the principal clay minerals namely, smectite, illite, kaolinite and vermiculite, and other minerals in lesser quantity. The percentage of the principal clay, mineral can vary significantly. The percent clay, size fraction and the salt concentration can also vary significantly. In view of the importance of undrained shear strength in geotechnical engineering practice, its behavior has been studied with respect to variation in salt concentration. Basically, two mechanisms control the undrained strength in clays, namely (a) cohesion or undrained strength is due to the net interparticle attractive forces, or (b) cohesion is due to the viscous nature of the double layer water. Concept (a) operates primarily for kaolinitic soil, and concept (b) dominates primarily for montmorillonitic soils. In Ariake clay, different clay minerals with different exchangeable cations and varying ion concentration in the pore water and varying nonclay size fraction are present. In view of this while both concepts (a) and (b) can coexist and operate simultaneously, one of the mechanisms dominates. For Isahaya clay, concept (a), factors responsible for an increase in level of flocculation and attractive forces result in higher undrained strength. Increase in salt concentration increases the remolded undrained strength at any moisture content. For Kubota and Kawazoe clays, concept (b) factors responsible for an expansion of diffuse double layer thickness, resulting in higher viscous resistance, increase the undrained shear strength, that is, as concentration decreases, the undrained strength increases at any moisture content.The liquid limit of Isahaya,a clay increases with increase in ion concentration and a marginal decrease is seen for both Kubota and Kawazoe clays, and their behavior has been explained satisfactorily,.