共查询到20条相似文献,搜索用时 31 毫秒
1.
Pijush Samui 《国际地质力学数值与分析法杂志》2012,36(1):100-110
This study employs two statistical learning algorithms (Support Vector Machine (SVM) and Relevance Vector Machine (RVM)) for the determination of ultimate bearing capacity (qu) of shallow foundation on cohesionless soil. SVM is firmly based on the theory of statistical learning, uses regression technique by introducing varepsilon‐insensitive loss function. RVM is based on a Bayesian formulation of a linear model with an appropriate prior that results in a sparse representation. It also gives variance of predicted data. The inputs of models are width of footing (B), depth of footing (D), footing geometry (L/B), unit weight of sand (γ) and angle of shearing resistance (?). Equations have been developed for the determination of qu of shallow foundation on cohesionless soil based on the SVM and RVM models. Sensitivity analysis has also been carried out to determine the effect of each input parameter. This study shows that the developed SVM and RVM are robust models for the prediction of qu of shallow foundation on cohesionless soil. Copyright © 2010 John Wiley & Sons, Ltd. 相似文献
2.
Support vector machine applied to settlement of shallow foundations on cohesionless soils 总被引:4,自引:0,他引:4
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. 相似文献
3.
The settlement of shallow foundation on cohesionless soil is a key parameter in the design of shallow foundation. The recently introduced relevance vector machine (RVM) technique is applied to predict the settlement of shallow foundation on cohesionless soils. RVM allows computation of the prediction intervals, taking into account the uncertainties of both the parameters and the data. It provides much sparser regressors without compromising performance, and kernel bases give a small but worthwhile improvement in performance. It also estimates the prediction variance. This study shows that compared to the available methods, RVM is better at determining the settlement of shallow foundation on cohesionless soil. 相似文献
4.
《Geomechanics and Geoengineering》2013,8(2):139-150
The influence of a non-coaxial model for granular soils on shallow foundation analyses is investigated. The non-coaxial plasticity theory proposed by Rudnicki and Rice (J. Mech. Phys. Solids 1975, 23, 371–394) is integrated into a Drucker–Prager model with both perfect plasticity and strain hardening. This non-coaxial model is numerically implemented into the finite-element program ABAQUS using a substepping scheme with automatic error control. The influence of the non-coaxial model on footing settlement and bearing capacity is investigated under various loading and boundary conditions. Compared with the predictions using conventional coaxial models, the non-coaxial prediction results indicate that the settlement of a footing increases significantly when the non-coaxial component of plastic strain rate is taken into consideration, although ultimate footing bearing capacities are not affected significantly. The non-coaxial model has a different effect on footing settlements under different loading and boundary conditions. In general, the discrepancies between coaxial and non-coaxial predictions increase with increasing rotation of principal stresses of the soil mass beneath a footing. It can be concluded that if the non-coaxial component of plastic strain rate is neglected in shallow foundation problems using the finite-element method, the results tend to be non-conservative when designs are dominated by settlement of footings. 相似文献
5.
In this paper, given an estimate of the bearing capacity of the soil, by treating settlement at a given load as a random variable and the evolution of settlement of footing on cohesionless soil with the increasing load as a stochastic process, a tri-level homogeneous Markov chain (TLHMC) model is proposed for prediction of settlement. Comparison of the predicted mean and bounds on settlements, obtained using TLHMC, with the respective field values obtained from literature shows that the stochastic evolution can be modelled using TLHMC with a correlation coefficient of 0.90. A methodology for reliability-based design of footings is also presented and its use is demonstrated through a numerical example. 相似文献
6.
Settlement of compacted ash fills 总被引:1,自引:0,他引:1
The coal ash is a by-product of coal-fired thermal power station. It is extensively used as a geo-material for landfill. The
compacted ash is used as a structural fill if it is properly characterized for load-bearing capacity and settlement. The main
objective of the present work is to characterize ash material and to evaluate its settlement characteristics. The ash is normally
compacted by vibration at or near optimum moisture for its performance as structural fill. The overt characteristics of ashes
are viewed similar to cohesionless soils. However, the mass behavior may have differences due to the subtle influence of chemical
and physical processes involved in its formation. The empirical and analytical methods predicting settlement of footing under
static loading require direct or indirect measurement of density and stress state in the deposit. In the present work, experimental
investigations for settlement prediction were carried out on compacted coal ash produced at Ropar thermal power station in
India, which was conveniently classified as ASTM class F ash. The settlement was experimentally obtained for the rigid plates having least dimension more than 0.3 m on ashes compacted
at varying degree of compaction. The predicted settlement based on the observed data of coal ash using conventional techniques
for soils was found to be conservative. A relationship between settlement and foundation size is proposed at varying compaction
to obtain the settlement of compacted ash. At a higher degree of compaction, the settlement of a foundation may not exceed
the allowable settlements in the working stress range. 相似文献
7.
Pijush Samui 《国际地质力学数值与分析法杂志》2012,36(11):1434-1439
The determination of ultimate capacity (Q) of driven piles in cohesionless soil is an important task in geotechnical engineering. This article adopts Multivariate Adaptive Regression Spline (MARS) for prediction Q of driven piles in cohesionless soil. MARS uses length (L), angle of shear resistance of the soil around the shaft (?shaft), angle of shear resistance of the soil at the tip of the pile (?tip), area (A), and effective vertical stress at the tip of the pile as input variables. Q is the output of MARS. The results of MARS are compared with that of the Generalized Regression Neural Network model. An equation has been also presented based on the developed MARS. The results show the strong potential of MARS to be applied to geotechnical engineering as a regression tool. Copyright © 2011 John Wiley & Sons, Ltd. 相似文献
8.
Ashis Kumar Bera Ambarish Ghosh Amalendu Ghosh 《Geotechnical and Geological Engineering》2007,25(3):315-325
This paper focuses on the effective utilization of pond ash, as foundation medium. A series of laboratory model tests have
been carried out using square, rectangular and strip footings on pond ash. The effects of dry density, degree of saturation
of pond ash, size and shape of footing on ultimate bearing capacity of shallow foundations are presented in this paper. Local
shear failure of a square footing on pond ash at 37% moisture content (optimum moisture content) is observed up to the values
of dry density 11.20 kN/m3 and general shear failure takes place at the values of dry density 11.48 kN/m3 and 11.70 kN/m3. Effects of degree of saturation on ultimate bearing capacity were studied. Experimental results show that degree of saturation
significantly affects the ultimate bearing capacity of strip footing. The effect of footing length to width ratio (L/B), on increase in ultimate bearing capacity of pond ash, is insignificant for L/B ≥ 10 in case of rectangular footings. The effects of size of footing on ultimate bearing capacity for all shapes of footings
viz., square, rectangular and strip footings are highlighted. 相似文献
9.
Site investigations that aim to sufficiently characterize a soil profile for foundation design, typically consist of a combination of in situ and laboratory tests. The number of tests and/or soil samples is generally determined by the budget and time considerations placed upon the investigation. Therefore, it is necessary to plan the locations of such tests to provide the most suitable information for use in design. This is considered the sampling strategy. However, the spatial variability of soil properties increases the complexity of this exercise. Results presented in this paper identify the errors associated with using soil properties from a single sample location on a pad foundation designed for settlement. Sample locations are distributed around the site to identify the most appropriate sample location and the relative benefits of taking soil samples closer to the center of the proposed footing. The variability of the underlying soil profile is also shown to a have a significant effect on the errors due to sampling location. Such effects have been shown in terms of the statistical properties of the soil profile. The performance of several common settlement relationships to design a foundation based on the results of a single sample location have also been examined. 相似文献
10.
In recent times, rapid urbanisation coupled with scarcity of land forces several structures to come up ever closer to each
other, which may sometime cause severe damage to the structures from both strength and serviceability point of view, and therefore,
a need is felt to devise simplified methods to capture the effect of footing interference. In the present study, an attempt
has been made to model the settlement behaviour of two strip footings placed in close spacing on layered soil deposit consisting
of a strong top layer underlying a weak bottom layer. Theory of elasticity is employed to derive the governing differential
equations and subsequently solved by the finite difference method. The perfectly rough strip footings are considered to be
resting on the surface of two-layer soil system, and the soil is assumed to behave as linear elastic material under a range
of static foundation load. The effect of various parameters such as the elastic moduli and thickness of two layers, clear
spacing between the footings and footing load on the settlement behaviour of closely spaced footings has been determined.
The variation of vertical normal stress at the interface of two different soil layers as well as at the base of the failure
domain also forms an important part of this study. The results are presented in terms of settlement ratio (ξδ), and their variation is obtained with the change in clear spacing between two footings. The present theoretical investigation
indicates that the settlement of closely spaced footings is found to be higher than that of single isolated footing, which
further reduces with increase in the spacing between the footings. 相似文献
11.
The scope of this paper is to present a macroelement model for shallow foundations encompassing the majority of combinations of soil and foundation–soil interface conditions that are interesting for practical applications. The basic idea of the formulation is to raise the common assumption that the surface of ultimate loads of the foundation is identified as a yield surface in the space of force parameters which the footing is subjected to. Instead, each non‐linear mechanism participating in the global response of the system is modelled independently and the surface of ultimate loads is retrieved as the combined result of all active mechanisms. This allows formulating each mechanism by respecting its particular characteristics and offers the possibility of activating, modifying or deactivating each mechanism according to the context of application. The model comprises three non‐linear mechanisms: (a) the mechanism of sliding at the soil–footing interface, (b) the mechanism of soil yielding in the vicinity of the footing and (c) the mechanism of uplift as the footing may get detached from the soil. The first two are irreversible and dissipative and are combined within a multi‐mechanism plasticity formulation. The third mechanism is reversible and non‐dissipative. It is reproduced with a phenomenological non‐linear hyperelastic model. The model is validated with respect to the existing results for shallow foundations under quasi‐static loading tests. It is shown that although the ultimate surface of the foundation is not explicitly used in the formulation of the model, the obtained force states by the model are always contained within it. Copyright © 2010 John Wiley & Sons, Ltd. 相似文献
12.
Accurate prediction of settlement for shallow footings on cohesionless soil is a complex geotechnical problem due to large uncertainties associated with soil. Prediction of the settlement of shallow footings on cohesionless soil is based on in situ tests as it is difficult to find out the properties of soil in the laboratory and standard penetration test (SPT) is the most often used in situ test. In data driven modelling, it is very difficult to choose the optimal input parameters, which will govern the model efficiency along with a better generalization. Feature subset selection involves minimization of both prediction error and the number of features, which are in general mutual conflicting objectives. In this study, a multi-objective optimization technique is used, where a non-dominated sorting genetic algorithm (NSGA II) is combined with a learning algorithm (neural network) to develop a prediction model based on SPT data based on the Pareto optimal front. Pareto optimal front gives the user freedom to choose a model in terms of accuracy and model complexity. It is also shown how NSGA II can be effectively applied to select the optimal parameters and besides minimizing the error rate. The developed model is compared with existing models in terms of different statistical criteria and found to be more efficient. 相似文献
13.
A practical and efficient approach of implementing second‐order reliability method (SORM) is presented and illustrated for cases related to foundation engineering involving explicit and implicit limit state functions. The proposed SORM procedure is based on an approximating paraboloid fitted to the limit state surface in the neighborhood of the design point and can be easily carried out in a spreadsheet. Complex mathematical operations are relegated to relatively simple user‐created functions. The failure probability is calculated automatically based on the reliability index and principal curvatures of the limit state surface using established closed‐form SORM formulas. Four common foundation engineering examples are analyzed using the proposed method and discussed: immediate settlement of a flexible rectangular foundation, bearing capacity of a shallow footing, axial capacity of a vertical single pile, and deflection of a pile under lateral load. Comparisons with Monte Carlo simulations are made. In the case of the laterally loaded pile, the friction angle of the soil is represented as a one‐dimensional random field, and pile deflections are computed based on finite element analysis on a stand‐alone computer package. The implicit limit state function is approximated via the response surface method using two quadratic models. Copyright © 2011 John Wiley & Sons, Ltd. 相似文献
14.
Maher Omar Khaled Hamad Mey Al Suwaidi Abdallah Shanableh 《Arabian Journal of Geosciences》2018,11(16):464
This research proposes the use of artificial neural network to predict the allowable bearing capacity and elastic settlement of shallow foundation on granular soils in Sharjah, United Arab Emirates. Data obtained from existing soil reports of 600 boreholes were used to train and validate the model. Three parameters (footing width, effective unit weight, and SPT blow count) are considered to have the most significant impact on the magnitude of allowable bearing capacity and elastic settlement of shallow foundations, and thus were used as the model inputs. Throughout the study, depth of footing was limited to 1.5 m below existing ground level and water table depth taken at the level of the footing. Performance comparison of the developed models (in terms of coefficient of determination, root mean square error, and mean absolute error) revealed that the developed artificial neural network models could be effectively used for predicting the allowable bearing capacity and elastic settlement. As such, the developed models can be used at the preliminary stage of estimating the allowable bearing capacity and settlements of shallow foundations on granular soils, instead of the conventional methods. 相似文献
15.
16.
Wei Dong Guo 《国际地质力学数值与分析法杂志》2000,24(2):135-163
Viscoelastic or creep behaviour can have a significant influence on the load transfer (t–z) response at the pile–soil interface, and thus on the pile load settlement relationship. Many experimental and theoretical models for pile load transfer behaviour have been presented. However, none of these has led to a closed‐form expression which captures both non‐linearity and viscoelastic behaviour of the soil. In this paper, non‐linear viscoelastic shaft and base load transfer (t–z) models are presented, based on integration of a generalized viscoelastic stress–strain model for the soil. The resulting shaft model is verified through published field and laboratory test data. With these models, the previous closed‐form solutions evolved for a pile in a non‐homogeneous media have been readily extended to account for visco‐elastic response. For 1‐step loading case, the closed‐form predictions have been verified extensively with previous more rigorous numerical analysis, and with the new GASPILE program analysis. Parametric studies on two kinds of commonly encountered loading: step loading, ramp (linear increase followed by sustained) loading have been performed. Two examples of the prediction of the effects of creep on the load settlement relationship by the solutions and the program GASPILE, have been presented. Copyright © 2000 John Wiley & Sons, Ltd. 相似文献
17.
L. G. Tham 《Computers and Geotechnics》1988,5(4):249-268
A numerical method is proposed for the analysis of rectangular footing resting on an elastic soil layer. The footing is represented by double spline elements and the elastic soil medium by finite layers. The effect of the rigidity of footing and the non-homogeneity of the soil on the behaviour of such foundation system is investigated, and the results are presented in form of design charts such that they may be used for hand calculation for the estimation of the settlement of footings for a wide range of practical cases. 相似文献
18.
By using an upper bound limit analysis in conjunction with finite elements and linear programming, the ultimate bearing capacity of two interfering rough strip footings, resting on a cohesionless medium, was computed. Along all the interfaces of the chosen triangular elements, velocity discontinuities were employed. The plastic strains were incorporated using an associated flow rule. For different clear spacing (S) between the two footings, the efficiency factor (ξγ) was determined, where ξγ is defined as the ratio of the failure load for a strip footing of given width in the presence of the other footing to that of a single isolated strip footing having the same width. The value of ξγ at S/B = 0 becomes equal to 2.0, and the maximum ξγ occurs at S/B = Scr/B. For S/B?Scr/B, the ultimate failure load for a footing becomes almost half that of an isolated footing having width (2B + S), and the soil mass below and in between the two footings deforms mainly in the downward direction. In contrast, for S/B>Scr/B, ground heave was noticed along both the sides of the footing. As compared to the available theories, the analysis provides generally lower values of ξγ for S/B>Scr/B. Copyright © 2007 John Wiley & Sons, Ltd. 相似文献
19.
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 (Nc), N values have been corrected (Nc) 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 Nc=Nc (X, Y, Z), where X, Y and Z are the coordinates of a point corresponding to Nc value, is to be approximated in which Nc 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 a ridge 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 © 2009 John Wiley & Sons, Ltd. 相似文献
20.
G. L. Sivakumar Babu Satyanarayana Murthy Dasaka 《Geotechnical and Geological Engineering》2008,26(1):37-46
The effect of directional behaviour of correlation structure of cone tip resistance on the bearing capacity of shallow strip
footing resting on cohesionless soil deposit in 2-D random field is analysed using probabilistic approach. The results obtained
from the analysis show that the assumption of perfect (or infinite) correlation of cone tip resistance data leads to lower
values of probability of failure. In contrast, the isotropic assumption of correlation behaviour based on vertical scale of
fluctuation leads to higher values of probability of failure. The results also show that the transformation model would play
a major role in the evaluation of variability of design property. In conclusion, the need for a proper evaluation methodology
for calculation of correlation lengths of soil properties and their influence in foundation design is highlighted. 相似文献