共查询到20条相似文献，搜索用时 31 毫秒
1.
Adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN) models have been extensively used to predict
different soil properties in geotechnical applications. In this study, it was aimed to develop ANFIS and ANN models to predict
the unconfined compressive strength (UCS) of compacted soils. For this purpose, 84 soil samples with different grain-size
distribution compacted at optimum water content were subjected to the unconfined compressive tests to determine their UCS
values. Many of the test results (for 64 samples) were used to train the ANFIS and the ANN models, and the rest of the experimental
results (for 20 samples) were used to predict the UCS of compacted samples. To train these models, the clay content, fine
silt content, coarse silt content, fine sand content, middle sand content, coarse sand content, and gravel content of the
total soil mass were used as input data for these models. The UCS values of compacted soils were output data in these models.
The ANFIS model results were compared with those of the ANN model and it was seen that the ANFIS model results were very encouraging.
Consequently, the results of this study have important findings indicating reliable and simple prediction tools for the UCS
of compacted soils. 相似文献
2.
This paper presents a review of the Adaptive Neuro-Fuzzy Inference System (ANFIS) in current use for geotechnical engineering-based studies, as well as some applications employed in resonant column testing, triaxial testing, and liquefaction triggering. Over the last few years, ANFIS has been used in many geotechnical engineering problems. A review of published literature reveals that ANFIS has been used successfully in footing response prediction, modeling of the friction angle of soils, tunnel stability analysis, estimating current-induced scour depth around pile groups, prediction of unconfined compressive strength, swelling potential of soils and permeability estimation. Some works have been selected to be described, as the others are acknowledged. The paper also presents ANFIS based models for coarse rotund sand–mica mixtures tested in triaxial and resonant column testing apparatuses and a modeling for liquefaction triggering. 相似文献
3.
A GIS model for preliminary hazard assessment of swelling clays,a case study in Harran plain (SE Turkey) 总被引：2，自引：1，他引：1
Swelling behavior of clayey soils regarded as a hidden disaster, causes a great deal of damage in light hydraulic structures
such as drinking water network, irrigation pipes or open canal linings through which water can easily leak and penetrate into
soil during loading and unloading stages. Early identification during site investigation and laboratory testing is extremely
important to ensure that the appropriate design strategy is adopted. The clay soils having swelling potential are generally
found in arid and semi-arid regions, such as in the Şanlıurfa-Harran plain located in the southeast of Turkey. The problems
associated with swelling clays occurred for the lightweight hydraulic structures constructed in Turkey have been met during
the construction of irrigation structures in the scope of Southeast Anatolian Project as the Turkey’s greatest water resources
project. Therefore, the identification of such soils and the assessment of their swelling potential parameters are necessary
for hazard mitigation planning and land-use management. In this scope, extensive geotechnical study is executed for an investigation
area. The samples were obtained from the Harran plain where many irrigation canal structures are constructed, and geotechnical
study was performed on these samples. Atterberg limit tests often provide the basic field information to substantiate the
soil’s swelling nature. The plasticity index (PI) and liquid limit (LL) values are also used extensively for classifying swelling
soil and should always be determined during preliminary investigations. Because of this, LL and PI are assessed by using geographical
information system (GIS)-based computer software, and LL and PI contour maps are created. Swelling percentages of the soil
samples were carried out on both undisturbed and compacted soil samples by using direct methods. As a result of this extensive
study, the values of swelling percentages determined for each location are used to obtain the swelling potential hazard map
of the area by means of a GIS program. The results of GIS analyses for this area indicate that the analyses based on a lot
of data introduce meaningful results for this study. It is expected that these maps will be a useful tool for planners and
engineers in their efforts to achieve better land-use planning and to decide necessary remedial measures. 相似文献
4.
Shahid Azam 《Geotechnical and Geological Engineering》2007,25(3):369-381
Soils containing expansive clays undergo swelling that can be both detrimental and beneficial in various applications. In
the Arabian Gulf coastal region, natural heterogeneous soils containing clay and sand (tills, shales, and clayey sands) support
most of the civil infrastructure systems. Likewise, mixes of clay and sand are used for local earthwork construction such
as roads and landfills. A clear understanding of the swelling behaviour of such soils is pivotal at the outset of all construction
projects. The main objective of this paper was to understand the evolution of swelling with increasing clay content in local
soils. A theoretical framework for clay–sand soils was developed using phase relationships. Laboratory investigations comprised
of mineralogical composition and geotechnical index properties of the clay and sand and consistency limits, swelling potential,
and morphology of clay–sand mixes. Results indicated that soil consistency of mixes of a local expansive clay and an engineered
sand depends on the weighted average of the constituents. Mixes with 10% clay through 40% clay capture the transition from
a sand-like behaviour to a clay-like behaviour. Influenced by the initial conditions and soil matrix, the swelling potential
of the investigated mixes correlated well with soil plasticity (SP(%) = 0.16 (I
p)1.188). The parameters sand void ratio and clay–water ratio were found to better explain the behaviour of blended clay–sand soils. 相似文献
5.
M. Mirzababaei M. Miraftab M. Mohamed P. McMahon 《Geotechnical and Geological Engineering》2013,31(1):173-182
Municipalities and recycling and environmental authorities are concerned about the growing amount of carpet waste produced by household, commercial and industrial sectors. It is reported that 500,000 tonnes of carpet waste fibre are plunged into landfills annually in the UK. In the United States of America, around 10 million tonnes of textile waste was generated in 2003. In geotechnical engineering, expansive clay soils are categorised as problematic soils due to their swelling behaviour upon increase in the moisture content. The problematic nature of such soils is intensified with the increase in the plasticity index. This paper presents results of a comprehensive investigation into utilisation of carpet waste fibres in order to improve the swelling characteristics of compacted cohesive soils. Therefore, two different clay soils with markedly different plasticity indices (i.e. 17.0 and 31.5 %) were treated with two different types of carpet waste fibre. Waste fibres were added to prepare specimens with fibre content of 1, 3 and 5 % by dry weight of soil. Soil specimens with different dry unit weights and moisture contents were prepared so as to the swelling behaviour of fibre reinforced compacted clays is completely attained under various scenarios. The results indicated that the behaviour of the fibre reinforced soils seems highly dependent on the initial compaction state and secondary on the moisture content. It was found that the swelling pressure drops rapidly as the percentage of fibre increases in samples prepared at the maximum dry unit weight and optimum moisture content. Reducing the dry unit weight, while maintaining constant moisture content or increasing the moisture content at constant dry unit weight was found to reduce the swelling pressure. 相似文献
6.
Application of the adaptive neuro-fuzzy inference system for prediction of soil liquefaction 总被引：1，自引：1，他引：0
The determination of liquefaction potential of soils induced by earthquake is a major concern and an essential criterion in the design process of the civil engineering structures. A purely empirical interpretation of the filed case histories relating to liquefaction potential is often not well constrained due to the complication associated with this problem. In this study, an integrated fuzzy neural network model, called Adaptive Neuro-Fuzzy Inference System (ANFIS), is developed for the assessment of liquefaction potential. The model is trained with large databases of liquefaction case histories. Nine parameters such as earthquake magnitude, the water table, the total vertical stress, the effective vertical stress, the depth, the peak acceleration at the ground surface, the cyclic stress ratio, the mean grain size, and the measured cone penetration test tip resistance were used as input parameters. The results revealed that the ANFIS model is a fairly promising approach for the prediction of the soil liquefaction potential and capable of representing the complex relationship between seismic properties of soils and their liquefaction potential. 相似文献
7.
Hydraulic conductivity is a dominant parameter in the design of engineered waste disposal facilities such as landfill liners and covers, lagoon liners and slurry walls. It is of interest to a geotechnical or geo-environmental engineer to develop a predictive method of determining the hydraulic conductivity of fine-grained soils, in order to assess its suitability as a liner material. To predict the hydraulic conductivity of soils, researchers and geotechnical engineers have attempted to correlate it with index properties of the soils, such as the liquid limit, void ratio and specific surface. Based on the present study a predictive method has been developed in this paper to predict the hydraulic conductivity in terms of void ratio and shrinkage index (Liquid limit – shrinkage limit) for remoulded fine-grained soils. Though the initial conditions for the soil will affect the hydraulic conductivity behaviour to some extent, both the void ratio and soil characteristics are primary factors in affecting the hydraulic conductivity. Therefore for predictive purpose, the study of hydraulic conductivity behaviour of remoulded fine-grained soils as presented in this paper can be found to be useful for compacted soils also. 相似文献
8.
Simulation-based optimization methods have been recently proposed for calibrating geotechnical models from laboratory and field tests. In these methods, geotechnical parameters are identified by matching model predictions to experimental data, i.e. by minimizing an objective function that measures the difference between the two. Expensive computational models, such as finite difference or finite element models are often required to simulate laboratory or field geotechnical tests. In such cases, simulation-based optimization might prove demanding since every evaluation of the objective function requires a new model simulation until the optimum set of parameter values is achieved. This paper introduces a novel simulation-based “hybrid moving boundary particle swarm optimization” (hmPSO) algorithm that enables calibration of geotechnical models from laboratory or field data. The hmPSO has proven effective in searching for model parameter values and, unlike other optimization methods, does not require information about the gradient of the objective function. Serial and parallel implementations of hmPSO have been validated in this work against a number of benchmarks, including numerical tests, and a challenging geotechnical problem consisting of the calibration of a water infiltration model for unsaturated soils. The latter application demonstrates the potential of hmPSO for interpreting laboratory and field tests as well as a tool for general back-analysis of geotechnical case studies. 相似文献
9.
In order to realize more benefits and to have more effective output from the mechanical ground improvement projects, the field soils are subjected to over consolidation. This process induces a characteristic yield stress in the compacted soil mass similar to that exhibited by the soil masses subjected to natural processes of over consolidation during their geological life time. In view of the absence of any documented geotechnical engineering literature on such an important topic, this paper intends to throw some useful light on compaction induced yield stress in fine-grained soils. A detailed discussion of various factors contributing to the induced yield stress as a consequence of compaction is done. The results of the present experimental study indicates that the values of compaction induced yield stress increase from dry side of optimum to optimum compacted state. This stress may tend to achieve an equilibrium value or decrease beyond optimum compacted state depending upon the contribution from the coarser fraction composing the soil. It is also illustrated that the soils subjected to same compactive effort exhibit different values of yield stress as a consequence of clay mineralogical composition of the soils. 相似文献
10.
Agapitus Ahamefule Amadi 《Environmental Earth Sciences》2013,70(6):2437-2442
Compacted soil–bentonite mixtures are finding wide application as buffer material for waste repositories for their favorable self-sealing qualities. The swelling properties of such materials which serve as a measure of their self-sealing capabilities and, thus, the efficiency of the repository in sealing off their contents from the environment are closely related to the chemistry of the leachate that emanate from the wastes. For this reason, the swelling parameters (namely swelling potential and pressure) of compacted lateritic soil–bentonite mixtures under consideration for use as barrier in municipal waste landfill were evaluated. Series of swelling potential and pressure tests were performed using variable content (0–10 %) of bentonite at predetermined optimum moisture content. Soil mixtures were compacted with British Standard Heavy compactive effort and saturated with processed tap water as well as three leachate solutions of varying ionic strength that were generated in active open dump landfills. Experimental results showed that swelling potential based on the free swell together with the maximum swell pressures of compacted soil mixtures measured at equilibrium increased approximately linearly with increase in the amount of bentonite when inundated with processed tap water and the three leachate solutions. On the other hand, these swelling parameters decreased as the ionic strength of the leachate solutions measured by their electrical conductivity increased for the various soil mixtures. These results provide an insight into the swelling behavior and the possible degradation in the efficiency of the proposed lateritic soil–bentonite mixtures in relation to their use as buffer material in waste landfills. 相似文献
11.
C. Kayadelen 《国际地质力学数值与分析法杂志》2008,32(9):1087-1106
Great efforts are required for determination of the effective stress parameter χ, applying the unsaturated testing procedure, since unsaturated soils that have the three‐phase system exhibit complex mechanical behavior. Therefore, it seems more reasonable to use the empirical methods for estimation of χ. The objective of this study is to investigate the practicability of using artificial neural networks (ANNs) to model the complex relationship between basic soil parameters, matric suction and the parameter χ. Five ANN models with different input parameters were developed. Feed‐forward back propagation was applied in the analyses as a learning algorithm. The data collected from the available literature were used for training and testing the ANN models. Furthermore, unsaturated triaxial tests were carried out under drained condition on compacted specimens. ANN models were validated by a part of data sets collected from the literature and data obtained from the current study, which were not included in the training phase. The analyses showed that the results obtained from ANN models are in satisfactory agreement with the experimental results and ANNs can be used as reliable tool for prediction of χ. Copyright © 2007 John Wiley & Sons, Ltd. 相似文献
12.
The compression index is a one of the important soil parameters that is essential to geotechnical designs. As the determination of the compression index from consolidation tests is relatively time-consuming, empirical formulas based on soil parameters can be useful. Over the decades, a number of empirical formulas have been proposed to relate the compressibility to other soil parameters, such as the natural water content, liquid limit, plasticity index, specific gravity, and others. Each of the existing empirical formulas yields good results for a particular test set, but cannot accurately or reliably predict the compression index from various test sets. In this study, an alternative approach, an artificial neural network (ANN) model, is proposed to estimate the compression index with numerous consolidation test sets. The compression index was modeled as a function of seven variables including the natural water content, liquid limit, plastic index, specific gravity, and soil types. Nine hundred and forty-seven consolidation tests for soils sampled at 67 construction sites in the Republic of Korea were used for the training and testing of the ANN model. The predicted results showed that the neural network could provide a better performance than the empirical formulas. 相似文献
13.
《Geomechanics and Geoengineering》2013,8(1):1-11
Experimental techniques of testing the mechanical properties of unsaturated soils are complex and difficult to conduct. As a consequence, complete sets of parameters that characterise the behaviour of unsaturated soils remain scarce and necessary. In this context, it has been found useful to gather the information obtained after some years of practice of the osmotic technique of controlling suction. As compared to the more documented axis-translation technique, the osmotic technique has its own advantages and drawbacks that are discussed in this paper, together with some potential future developments. The osmotic method has been developed by soil scientists in the 1960s and adapted to geotechnical testing in the early 1970s. This paper presents the osmotic technique and comments on its advantages (including suction condition close to reality and higher suctions easily attained) and drawbacks (including some concern with the membrane resistance and some membrane effects in the suction/concentration calibration). Various applications to geotechnical testing are presented such as the determination of the water retention curve, oedometer and triaxial testing procedures and the determination of the permeability of unsaturated soils. Recent developments, that include the extension of the method up to high suctions (10 MPa) are also described, together with some recent and novel applications such as data from high controlled suction oedometer compression test and the determination of the oil/water retention properties of oil reservoir chalks. 相似文献
14.
This study examined the spatial-temporal variations in seismicity parameters for the September 10th, 2008 Qeshm earthquake in south Iran. To this aim, artificial neural networks and Adaptive Neural Fuzzy Inference System (ANFIS) were applied. The supervised Radial Basis Function (RBF) network and ANFIS model were implemented because they have shown the efficiency in classification and prediction problems. The eight seismicity parameters were calculated to analyze spatial and temporal seismicity pattern. The data preprocessing that included normalization and Principal Component Analysis (PCA) techniques was led before the data was fed into the RBF network and ANFIS model. Although the accuracy of RBF network and ANFIS model could be evaluated rather similar, the RBF exhibited a higher performance than the ANFIS for prediction of the epicenter area and time of occurrence of the 2008 Qeshm main shock. A proper training on the basis of RBF network and ANFIS model might adopt the physical understanding between seismic data and generate more effective results than conventional prediction approaches. The results of the present study indicated that the RBF neural networks and the ANFIS models could be suitable tools for accurate prediction of epicenteral area as well as time of occurrence of forthcoming strong earthquakes in active seismogenic areas. 相似文献
15.
A dual-porosity model for the study of chemical effects on the swelling behaviour of MX-80 bentonite
Significant chemical influence on the swelling potential of MX-80 bentonite was observed during swelling tests where specimens were hydrated with highly concentrated brine. The maximum swelling pressure for specimens hydrated with brine was about 30% of the maximum swelling pressure for the same specimens hydrated with de-ionized water. The maximum swelling pressure was attained within tens of hours of brine infiltration and further decreased by half within a year. A fully coupled hydro–mechanical–chemical (HMC) dual-porosity model is proposed in this paper to interpret the swelling behaviour of MX-80 when infiltrated with brine. The dependence of hydraulic and mechanical properties on such factors as porosity, salinity and water content was investigated. A nonlinear elastic constitutive model was proposed to correlate the swelling pressure with the variation in the microporosity. The chemical effects on the mechanical behaviour were coupled at the micropore level. A number of relationships have been developed for MX-80, i.e. micropore permeability as a function of void ratio, water retention characteristics of micropores and macropores, micropore dependence on water content and the diffusion coefficients of the two types of pore structure. The proposed model was successful in reproducing both quantitatively and qualitatively the experimental results from two sets of infiltration experiments on compacted MX-80 bentonite.
相似文献16.
人工神经网络已应用在岩土工程的各个方面。针对常用的BP网络的不足之处,建立了基于自适应神经模糊推理系统（ANFIS）的单桩竖向极限承载力预测模型。利用文献中桩的载荷试验数据来训练ANFIS网络,确定了网络参数。研究结果表明,同常用的BP网络相比,ANFIS预测模型具有学习速度快,拟合能力较好,训练结果唯一等优点,该方法是一种有效地预测单桩极限承载力的方法。 相似文献
17.
《Geomechanics and Geoengineering》2013,8(4):213-221
This paper presents results from an experimental study performed on natural and compacted expansive soils in different loose and dense states using principally osmotic oedometers. The loose soils showed significant shrinkage, while the dense soils produced a swelling accumulation during the suction cycles. These cycles induced an equilibrium stage, which indicates an elastic behaviour of the samples under suction cycles. At the end of suction cycles, a loading/unloading test was performed on all samples at different constant suctions to define LC (loading collapse) yield curve as well as the newly defined SC (saturation curve) yield curve. Generally, the suction cycles for the looser soils approached the LC and SC yield curves while they became the same at the equilibrium state. For the denser soils producing the swelling strain accumulation, the unique LC and SC curves were activated together. Additionally, we found that at the equilibrium stage, both initially loose and dense samples presented the same mechanical parameters. In other words, the LC or SC yield curves superimposed for different initial states of the samples at the equilibrium stage. Moreover, these compression curves provided sufficient data to propose a simplified model for the mechanical behaviour of the swelling soils at the equilibrium stage. 相似文献
18.
In recent years, geotechnical engineers are using tyre waste to alter the properties of soil for providing sustainable solutions to complex engineering problems. It is noted that black cotton soil, which is expansive in nature, covers a major portion of the Indian sub-continent, such as the Deccan plateau, Malwa plateau and a portion of Gujarat and poses challenging problems to infrastructural development in the region. In the present study, authors have characterised the geotechnical properties of black cotton soil, which is partially replaced with 4.75 mm passing – 2 mm retained (coarse fraction) and 2.0 mm passing - 75 micron retained (fine fraction) shredded tyre waste. The results of the experimental studies clearly show that partial replacement of black cotton soil with shredded tyre waste alters the geotechnical properties favourable to engineering applications and greatly reduces the swelling potential of the black cotton soil. It is noted that instead of fine fraction (2.0–0.075 mm), replacement with coarse fraction (4.75–2.00 mm) of shredded tyre waste can better be used for light weight fill behind the retaining walls as well as for embankment construction as it helps in reducing swelling pressure as well as improving the strength properties. 相似文献
19.
Clay deposits in Oltu-Narman basins (Erzurum, northern Turkey) have been studied to determine their engineering properties
and to evaluate their uses for geotechnical applications. These deposits are concentrated in two different stratigraphic horizons
namely the Late Oligocene and the Early Miocene sequences. Clay-rich fine-grained sedimentary units are deposited in shallow
marine and lagoonar mixed environments. Their clay minerals originated by the alteration of Eocene calc-alkaline island-arc
volcanics, preferably from pyroclastics (trachite and andesite flow), which form the basement for the Oltu depression. Smectite
group clay minerals are found abundant in clay deposits. The experimental results show that the clay soils have high plasticity
behaviors and low hydraulic conductivity properties. The optimum water content, the free swell, and the swelling pressure
of clay samples decreased and the maximum dry unit weight of clay samples increased under high temperature. Consequently,
it is concluded that the expanding of clay soils is an important soil problem that cannot be avoided in the significant parts
of Oltu city and its villages. However, the soils of clay-rich layers in the outcrops-section of clay deposits can be successfully
used to build compacted clay liners for landfill systems and to construct vertical and horizontal barriers for protection
of ground water and for preventing soil pollution in geotechnical applications. 相似文献
20.
Planning Geotechnical Investigation Using ANFIS 总被引：2，自引：2，他引：0
Bojan Žlender Primož Jelušič Djamalddine Boumezerane 《Geotechnical and Geological Engineering》2012,30(4):975-989
Engineering experience may be written in mathematical form by using adaptive network-based fuzzy inference system (ANFIS). In this article we propose a method to use engineering experience and build a model, which can be used as a systematic decision support tool for engineers dealing with new problems. Planning geotechnical investigations is based on experience, which are used to obtain optimal number of investigation points, field and laboratory tests. To achieve this objective we define minimum number of investigation points and several input parameters which could increase or decrease the number of investigation points. The expert’s evaluations were put in a table, from which we generate the basis of the system. The paper presents a concept for planning geotechnical investigation for buildings using ANFIS and practical examples show its usefulness. 相似文献