Search results

The purpose of this paper is to examine the feasibility of committee neural network (CNN) theory for the improvement of accuracy and consistency of the neural network model on the estimation of preconsolidation pressure from the field piezocone measurements.

In this study, CNN theory is introduced to improve the initial weight dependency of the neural network model on the prediction of preconsolidation pressure of soft clay from a piezocone test result. It was found that the proposed CNN model can improve the initial weight dependency of the NN model and provide a more consistent and precise inference result than existing NN models, as well as empirical and theoretical models.

It was found that the CNN overcomes the initial weight dependency of the single neural network model. Various committees of the single multilayer perceptrons (MLPs) were tested. It was found that if eight single MLPs, which have the same structure but have been trained with a different initial weight and bias, are accumulated in the committee with the same weighting factor, any variation on the prediction of the preconsolidation pressure from the piezocone test result can be simply and successfully eliminated.

In recent years, ANN has been found to be a powerful theory for analyzing complex relationships involving a multitude of variables, on many geotechnical applications. However, single MLP, when repeatedly trained on the same patterns, tends to reach different minima of the objective function each time and hence give a different set of neuron weights, because the solution is not unique for noisy data, as in most geotechnical problems. The authors observed that a committee neural network system is able to provide improved performance compared with a single optimal neural network.

Effective explicit algorithms for integrating complex elastoplastic constitutive models, such as those belonging to the Cam clay family, are described. These automatically divide the applied strain increment into subincrements using an estimate of the local error and attempt to control the global integration error in the stresses. For a given scheme, the number of substeps used is a function of the error tolerance specified, the magnitude of the imposed strain increment, and the non‐linearity of the constitutive relations. The algorithms build on the work of Sloan in 1987 but include a number of important enhancements. The steps required to implement the integration schemes are described in detail and results are presented for a rigid footing resting on a layer of Tresca, Mohr‐Coulomb, modified Cam clay and generalised Cam clay soil. Explicit methods with automatic substepping and error control are shown to be reliable and efficient for these models. Moreover, for a given load path, they are able to control the global integration error in the stresses to lie near a specified tolerance. The methods described can be used for exceedingly complex constitutive laws, including those with a non‐linear elastic response inside the yield surface. This is because most of the code required to program them is independent of the precise form of the stress‐strain relations. In contrast, most of the implicit methods, such as the backward Euler return scheme, are difficult to implement for all but the simplest soil models.

This study aims to predict the volume changes and collapse potential (CP) associated with the changes in soil suction by using the pressure cell and the effect of initial load on soil suction. Three types of gypseous soils have been experimented in this study, sandy gypseous soil from different parts of Iraq. A series of collapse tests were carried out using the oedometer device [single oedometer test (SOT) and double oedometer test (DOT)]. In addition, large-scale model with soil dimensions 700 × 700 × 600 mm was used to show the effect of water content changes in different relations (collapse with time, stress with time, suction with time, etc.).

A series of collapse tests were carried out using the oedometer device (SOT and DOT). In addition, a large-scale model with soil dimensions 700 × 700 × 600 mm was used to show the effect of water content changes in different relations (collapse with time, stress with time, suction with time, etc.).

The CP increases with the increasing of the void ratio for each soil. For each soil, the CP decreased when the initial degree of saturation increased. Kerbala soil with gypsum content (30%) revealed collapse value higher than Tikrit soil with gypsum content (55%) under the same initial conditions of water content and density, this is because the higher the Cu value of Kerbala soil is, the more well-graded the soil will be. Upon wetting, the smaller particles or fractions of the well-graded soil tend to fill in the existing voids, resulting in a lower void ratio as compared to the poorly graded one. Consequently, soils with high Cu value tend to collapse more than poorly graded ones. The compressibility of the soil is low when loaded under unsaturated condition, the CP for samples tested in the DOTs under stress level 800 kPa are greater than those obtained from collapse test at a stress level of 200 kPa.

The initial value of suction for all soils increases with initial water content decreases.

Elasto‐plastic models based on critical state formulations have been successful in describing many of the most important features of the mechanical behaviour of soils. This review paper deals with the applications of this class of models to the numerical analysis of geotechnical problems. After a brief overview of the development of the models, the basic critical state formulation is presented together with the main modifications which have actually been used in computational applications. The problems associated with the numerical implementation of this type of models are then discussed. Finally, a summary of reported computational applications and some specific examples of analyses of geotechnical problems using critical state models are presented.

It is well known that the prefabricated vertical drain (PVD) installation process generates a significant soil disturbance around PVD. This disturbed zone significantly affects the rate of settlement and excess pore pressure dissipation. However, the characteristics of these zones were still uncertain and difficult to quantify; there remains large discrepancy among researchers. This study aims to develop a simple analytical solution for radial consolidation analysis of PVD-installed deposit considering mandrel-induced disturbance.

The proposed solution takes into account the nonlinear distributions of both horizontal hydraulic conductivity and compressibility toward the drain. The proposed solution was applied to analyze field behavior of test embankment in New South Wales, Australia.

Both effects significantly increased the time required to achieve a certain degree of consolidation. The effect of hydraulic conductivity on the consolidation rate was more significant than the effect of compressibility variation. And, the increased compressibility in the soil-disturbed zone due to mandrel installation significantly increased vertical strain of the PVD-improved soil deposit. The predicted results using the proposed analytical solution were in good agreement with the field measurements.

A geotechnical engineer could use the proposed analytical solution to predict consolidation behavior of drainage-installed ground.

Consolidation behavior of PVD-installed ground could be reasonably predicted by using the proposed solution with considering variations of both hydraulic conductivity and compressibility due to PVD installation.

Reinforced lightweight soil (RLS) consisting of dredged soil, cement, air‐foam, and waste fishing net is considered to be an eco‐friendly backfilling material because it provides a means to recycle both dredged soil and waste fishing net. It may be difficult to find an optimum mixing ratio of RLS considering the design criteria and the construction's situation using the limited test results because the unconfined compressive strength is complicatedly influenced by various mixing ratios of admixtures. As a result, in order to expedite the field application of RLS, an appropriate prediction method is needed. The paper aims to address these issues.

In this study, an artificial neural network (ANN) model that was based on experimental test results performed on various mixing ratios, was developed to predict the unconfined compressive strength of RLS.

It was found that the unconfined compressive strength of RLS at a given mixing ratio could be reasonably estimated using the developed neural network model. In addition, sensitivity analysis was also conducted to evaluate the effect of mixing conditions on the compressive strength of RLS.

RLS is considered to be environmentally friendly because it provides a means to recycle both dredged soil and waste fishing net. The contractors could use the proposed ANN model as an alternative method to predict the strength of RLS with a specific mixing ratio.

This paper reveals that the developed ANN model can be served as a simple and reliable predictive tool for the strength of RLS without excessive laboratory tests for various admixture contents. An optimum admixture ratio of composed materials to get a designed strength could be easily found by using the proposed ANN model.

This paper aims to determine how the viscosity and curing agent content affect the flowability of moist silica sand granules. In addition, a coating device was designed according to the flow properties of silica sand granules.

The flowability of silica sand granules premixed with two curing agents of different viscosities is studied using a Jenike shear apparatus. An open-ended device was used in discharge testing of sand granules with a design based on the variable dip angle of the two plates and variable outlet size.

The test results show that increasing the curing agent content would significantly decrease the flowability of silica sand granules, and a curing agent of higher viscosity has a greater effect on the flowability of silica sand. The presence of a curing agent strengthens the cohesion among sand granules, lubricates them and restrains their deformation. The shape function of the coating device was obtained by theoretical derivation.

The flow properties provide a valuable theoretical guidance for the design of coating device for sand mold printing.

This paper deals with experimental work on flow properties of silica sand granules with different viscosities and curing agent content. The shape function of a wedge-shaped coating device is obtained based on experimental data.

Stock selection has long been identified as a challenging task. This line of research is highly contingent upon reliable stock ranking for successful portfolio construction. The purpose of this paper is to employ the methods from computational intelligence (CI) to solve this problem more effectively.

The authors develop a risk-adjusted strategy to improve upon the previous stock selection models by two main risk measures – downside risk and variation in returns. Moreover, the authors employ the genetic algorithm for optimization of model parameters and selection for input variables simultaneously.

It is found that the proposed risk-adjusted methodology via maximum drawdown significantly outperforms the benchmark and improves the previous model in the performance of stock selection.

Future work considers an extensive study for the risk-adjusted model using other risk measures such as Value at Risk, Block Maxima, etc. The authors also intend to use financial data from other countries, if available, in order to assess if the method is generally applicable and robust across different environments.

The authors expect this risk-adjusted model to advance the CI research for financial engineering and provide an promising solutions to stock selection in practice.

The originality of this work is that maximum drawdown is being successfully incorporated into the CI-based stock selection model in which the model's effectiveness is validated with strong statistical evidence.

“Inevitable and profound” are the changes in the distribution world which John Harvey foresees for the rest of the decade. The number of operators in both the own‐account and public sectors will decline; there will be increasing polarisation between the small, local distribution company and the national network companies. Enhanced service levels will inevitably arise as a result of pressure from both manufacturers and their customers. Significantly, John Harvey visualises, in the short to medium term, an inhibition on investment in high technology materials handling, automation, and hardware; he sees more future for the pallet and picking truck than he does for automated warehouses and retrieval systems. SPD is of course one of the leading companies in the distribution sector; it employs nearly 8,000 people with a turnover of £175m from express parcels, haulage, warehousing and distribution and other functions. John Harvey gave this paper at a conference sponsored by Rolatruc Limited of Slough, and it was held in London in February.

In 2001, the first municipal consolidation occurred in over 100 years in Michigan between two cities and one village in Michigan's rural Upper Peninsula, forming the City of Iron River. The three units of government combined to have a population of 3,391 within the newly incorporated boundaries. Driving the consolidation was continual population loss and erosion of the economic tax base of the individual municipal governments since the 1960s. This study sought to assess whether, five years after the consolidation, the governments had saved money as compared to a peer group of governments in Michigan. The findings indicate that the new city of Iron River was able to provide some evidence of cost control and savings following the consolidation.