Browsing by Author "Erzin, Y"

Now showing 1 - 20 of 23
  • No Thumbnail Available
    Item
    Artificial neural network models for predicting electrical resistivity of soils from their thermal resistivity
    Erzin, Y; Rao, BH; Patel, A; Gumaste, SD; Singh, DN
    The knowledge of soil electrical and thermal resistivities is essential for several engineering projects such as laying of high voltage buried power cables, nuclear waste disposal, design of fluidized thermal beds, ground modification techniques etc. This necessitates precise determination of these resistivities, and relationship between them, which mainly depend on the soil type, its origin, compaction density and saturation. Such a relationship would also be helpful for determining one of these resistivities, if the other one is known. With this in view, efforts were made to develop artificial neural network (ANN) models that can be employed for estimating the soil electrical resistivity based on its soil thermal resistivity and the degree of saturation. To achieve this, measurements of electrical and thermal resistivities were carried out on different types soils compacted at different densities and moisture contents. These models were validated by comparing the predicted results vis-A-vis those obtained from experiments. The efficiency of these ANN models in predicting the soil electrical resistivity has been demonstrated, if its thermal resistivity is known. These ANN models are found to yield better results as compared to the generalized relationships proposed by the earlier researchers. (C) 2009 Elsevier Masson SAS. All rights reserved.
  • No Thumbnail Available
    Item
    Swell pressure prediction by suction methods
    Erzin, Y; Erol, O
    Soil suction is the most relevant soil parameter for characterization of the swell behavior. An attempt was made to predict swell pressures from soil suction measurements. In this study, Na-bentonite was mixed with kaolinite in the ratios of 5, 10, 15, 20 and 25% of dry kaolinite weight to obtain soils in a wide range of plasticity indices (i.e. 30, 50, 68, 84 and 97%). Suction measurements using thermocouple psychrometer technique were made on statically compacted specimens. The dependence of soil suction on water content, dry density and bentonite content was examined. Soil suction was correlated to the soil properties, namely, water content, plasticity index, dry density, cation exchange capacity and specific surface area using multiple regression analyses. The correlations revealed a simple regression equation for a quick prediction of soil suctions from easily determined soil properties. In order to investigate soil suction versus swell pressure behavior, the results of standard constant volume swell tests (ASTM, 1990) performed on statically compacted samples of these clay mixtures were used. A linear relationship was established between the logarithm soil suction and the swell pressure. It was also found that an experimental relationship which would directly relate the initial soil suction to the swell pressure can be established. (c) 2007 Elsevier B.V All rights reserved.
  • No Thumbnail Available
    Item
    Strength of sands in wedge shear, triaxial shear, and shear box tests
    Mirata, T; Erzin, Y
    Limited tests had indicated peak drained values of angle of internal friction (of gravelly sands measured in the cylindrical wedge shear test (cylwest) to be relatively closer to the (expected from plane strain tests than from triaxial tests. Such a difference was not obtained between the results of the prismatic wedge shear test (priswest) and the triaxial test on gravels and crushed rock. In this study, six sands with <3.35 mm particles were tested. It was seen that the main reason for the difference between the phi values from cylwests and priswests was the difference in the angle delta between the shear plane and the bedding planes. Cylwests, in which delta was nearly the same as in triaxial tests, gave results close to those expected from plane strain tests, and almost identical results to those obtained from shear box tests on specimens so prepared as to make delta the same.
  • No Thumbnail Available
    Item
    The use of neural networks for CPT-based liquefaction screening
    Erzin, Y; Ecemis, N
    This study deals with development of two different artificial neural network (ANN) models: one for predicting cone penetration resistance and the other for predicting liquefaction resistance. For this purpose, cone penetration numerical simulations and cyclic triaxial tests conducted on Ottawa sand-silt mixes at different fines content were used. Results obtained from ANN models were compared with simulation and experimental results and found close to them. In addition, the performance indices such as coefficient of determination, root mean square error, mean absolute error, and variance were used to check the prediction capacity of the ANN models developed. Both ANN models have shown a high prediction performance based on the performance indices. It has been demonstrated that the ANN models developed in this study can be employed for predicting cone penetration and liquefaction resistances of sand-silt mixes quite efficiently.
  • No Thumbnail Available
    Item
    The Use of Neural Networks for the Prediction of Zeta Potential of Kaolinite
    Erzin, Y; Yukselen-Aksoy, Y
    The sign and the magnitude of the zeta potential must be known for many engineering applications. For clay soils, it is usually negative, but it is strongly dependent on the pore fluid chemistry. However, measurement of zeta potential time is time-consuming and requires special and expensive equipment. In this study, the prediction of zeta potential of kaolinite has been investigated by artificial neural networks (ANNs) and multiple regression analyses (MRAs). To achieve this, ANN and MRA models based on zeta potential measurements of kaolinite in the presence of salt and heavy metal cations at different pH values have been developed. The results of the models were compared with the experimental results. The performance indices, including coefficient of determination, root mean square error, mean absolute error, and variance, were used to assess the performance of the prediction capacity of the models developed in this study. The obtained indices make it clear that the constructed ANN models were able to predict zeta potential of kaolinite quite efficiently and outperformed the MRA models. Results showed that ANN models can be used satisfactorily to predict zeta potential of kaolinite as a rapid inexpensive substitute for laboratory techniques.
  • No Thumbnail Available
    Item
    Artificial neural networks approach for ζ potential of Montmorillonite in the presence of different cations
    Yukselen-Aksoy, Y; Erzin, Y
    In this study, the zeta potential of montmorillonite in the presence of different chemical solutions was modeled by means of artificial neural networks (ANNs). Zeta potential of the montmorillonite was measured in the presence of salt cations, Na+, Li+ and Ca2+ and metals Zn2+, Pb2+, Cu2+, and Al3+ at different pH values, and observed values pointed to a different behavior for this mineral in the presence of salt and heavy metal cations. Artificial neural networks were successfully developed for the prediction of the zeta potential of montmorillonite in the presence of salt and heavy metal cations at different pH values and ionic strengths. Resulting zeta potential of montmorillonite shows different behavior in the presence of salt and heavy metal cations, and two ANN models were developed in order to be compared with experimental results. The ANNs results were found to be close to experimentally measured zeta potential values. The performance indices such as coefficient of determination, root mean square error, mean absolute error, and variance account for were used to control the performance of the prediction capacity of the models developed in this study. These indices obtained make it clear that the predictive models constructed are quite powerful. The constructed ANN models exhibited a high performance according to the performance indices. This performance has also shown that the ANNs seem to be a useful tool to minimize the uncertainties encountered during the soil engineering projects. For this reason, the use of ANNs may provide new approaches and methodologies.
  • No Thumbnail Available
    Item
    Artificial neural network (ANN) models for determining hydraulic conductivity of compacted fine-grained soils
    Erzin, Y; Gumaste, SD; Gupta, AK; Singh, DN
    This study deals with development of artificial neural networks (ANNs) and multiple regression analysis (MRA) models for determining hydraulic conductivity of fine-grained soils. To achieve this, conventional falling-head tests, oedometer falling-head tests, and centrifuge tests were conducted on silty sand and marine clays compacted at different dry densities and moisture contents. Further, results obtained from ANN and MRA models were compared vis-a-vis experimental results. The performance indices such as the coefficient of determination, root mean square error, mean absolute error, and variance were used to assess the performance of these models. The ANN models exhibit higher prediction performance than the MRA models based on their performance indices. It has been demonstrated that the ANN models developed in the study can be employed for determining hydraulic conductivity of compacted fine-grained soils quite efficiently.
  • No Thumbnail Available
    Item
    Factors influencing the crushing strength of some Aegean sands
    Erzin, Y; Patel, A; Singh, DN; Tiga, MG; Yilmaz, I; Srinivas, K
    Engineering properties of sands mainly depend on the integrity of the particles, which in turn has a strong bearing on their crushing strength. Seven different Aegean sands were tested for mineralogy, particle shape, size and specific gravity and the influence of aspect ratio, particle composition, particle shape and size on the crushing strength was examined. As the Aegean sands have a small range of sphericity and roundness, crushing strength tests were also performed on five Anatolian sands. A multiple regression analysis was carried out and an equation proposed to determine the crushing strength value of the Aegean sands. The computed values were found to be in good agreement with those obtained from the experimental investigations. It is concluded that the equation is sufficiently accurate to be a useful, time- and cost-effective way of obtaining crushing strength estimations at the preliminary stage of site investigations.
  • No Thumbnail Available
    Item
    Investigations into factors influencing the CBR values of some Aegean sands
    Erzin, Y; Türköz, D; Tuskan, Y; Yilmaz, I
    The California Bearing Ratio (CBR) value of the soils is very important for geotechnical engineering and earth structures. A CBR value is affected by the soil type and different soil properties. With this in view, in this paper, an attempt has been made for investigating the factors that affect the CBR values of some Aegean sands collected from nine different locations in Manisa (Turkey). The sand samples were tested for mineralogy, particle shape and size, and specific gravity. The CBR tests were then performed on these samples at different dry densities to examine the influence of dry density, relative density, water content, and particle shape and size on the CBR value. Multiple Regression Analysis (MRA) was performed to predict the CBR value of the sands by using the experimental results. Moreover, several performance indices, such as coefficient of correlation and variance account for mean absolute error and root mean square error, were calculated to check the prediction capacity of the proposed MR equation. The obtained indices make it clear that the equation derived from the samples used in this study applies well, with an acceptable accuracy, to the CBR estimation at the preliminary stage of site investigations. (c) 2016 Sharif University of Technology. All rights reserved.
  • No Thumbnail Available
    Item
    THE USE OF SELF-ORGANIZING FEATURE MAP NETWORKS FOR THE PREDICTION OF THE CRITICAL FACTOR OF SAFETY OF AN ARTIFICIAL SLOPE
    Erzin, Y; Nikoo, M; Nikoo, M; Cetin, T
    In this study, the performance of three different self organization feature map (SOFM) network models denoted as SOFM1, SOFM2, and SOFM3 having neighborhood shapes, namely, SquareKohonenful, LineKohonenful, and Diamond-Kohenenful, respectively, to predict the critical factor of safety (F-s) of a widely-used artificial slope subjected to earthquake forces was investigated and compared. For this purpose, the reported data sets by Erzin and Cetin (2012) [7], including the minimum (critical) F-s values of the artificial slope calculated by using the simplified Bishop method, were utilized in the development of the SOFM models. The results obtained from the SOFM models were compared with those obtained from the calculations. It is found that the SOFM1 model exhibits more reliable predictions than SOFM2 and SOFM3 models. Moreover, the performance indices such as the determination coefficient, variance account for, mean absolute error, root mean square error, and the scaled percent error were computed to evaluate the prediction capacity of the SOFM models developed. The study demonstrates that the SOFM1 model is able to predict the F-s value of the artificial slope, quite efficiently, and is superior to the SOFM2 and SOFM3
  • No Thumbnail Available
    Item
    Artificial neural network models for predicting soil thermal resistivity
    Erzin, Y; Rao, BH; Singh, DN
    Thermal properties of soils are of great importance in view of the modern trends of utilizing the subsurface for transmission of either heated fluids or high power currents. For these situations, it is essential to estimate the resistance offered by the soil mass in dissipating the heat generated through it. Several investigators have tried to develop mathematical and theoretical models to estimate soil thermal resistivity. However, it is evident that these models are not efficient enough to predict accurate thermal resistivity of soils. This is mainly due to the fact that thermal resistivity of soils is a complex phenomenon that depends upon various parameters viz., type of the soil, particle size distribution and its compaction characteristics (i.e., dry density and moisture content). To overcome this, Artificial Neural Network (ANN) models, which are based on experimentally obtained thermal resistivity values for clay, silt, silty-sand, fine- and coarse-sands, have been developed. Incidentally, these soils are the most commonly encountered soils in nature and exhibit entirely different characteristics. The thermal resistivity of these soils, corresponding to their different compaction states, was obtained with the help of a laboratory thermal probe and compared vis-a-vis those obtained from the ANN model. The thermal resistivity of these soils obtained from ANN models and experimental investigations are found to snatch extremely well. The performance indices such as coefficient of determination, root mean square error, mean absolute error, and variance account for were used to control the performance of the prediction capacity of the models developed in this study. In addition to this, thermal resistivity of these soils obtained from ANN models were compared with those computed from the empirical relationships reported in the literature and were found to be superior. The study demonstrates the utility and efficiency of the ANN model for estimating thermal resistivity of soils. (c) 2007 Elsevier Masson SAS. All rights reserved.
  • No Thumbnail Available
    Item
    A case study of crushing resistance of Anatolian sands at lower and higher density
    Erzin, Y; Yilmaz, I
    Particle breakage occurs when the stresses imposed on soil particles exceed their strength. In order to determine the crushing resistance, Anatolian sands were collected from three different locations in Turkey. Mineralogical, particle shape and size characteristics were first determined by laboratory testing and compaction and triaxial tests then undertaken. Particle breakage factors were calculated from the initial and final gradations of the samples. It was noted that the sample containing a third calcite experienced higher particle breakage.
  • No Thumbnail Available
    Item
    Artificial neural networks approach for swell pressure versus soil suction behaviour
    Erzin, Y
    In this study, the swell pressure versus soil suction behaviour was investigated using artificial neural networks (ANNs). To achieve this, the results of the total suction measurements using thermocouple psychrometer technique and constant-volume swell tests in oedometers performed on statically compacted specimens of Bentonite-Kaolinite clay mixtures with varying soil properties were used. Two different ANN models have been developed to predict the total suction and swell pressure. The ANNs results were compared with the experimental values and found close to the experimental results. Moreover, several performance indices such as correlation coefficient, variance account for (VAF), and root mean square error (RMSE) were calculated to check the prediction capacity of the ANN models developed. Both ANN models have shown a high prediction performance based on the performance indices. Therefore, it can be concluded that the initial soil suction is the most relevant state of suction that characterizes the potential swell pressures.
  • No Thumbnail Available
    Item
    The use of neural networks for the prediction of swell pressure
    Erzin, Y
    Artificial neural networks (ANNs) are a new type of information processing system based on modeling the neural system of human brain. The prediction of swell pressures from easily determined soil properties, namely, initial dry density, initial water content, and plasticity index, have been investigated by using artificial neural networks. The results of the constant volume swell tests in oedometers, performed on statically compacted specimens of Bentonite-Kaolinite clay mixtures with varying soil properties, were trained in an ANNs program and the results were compared with the experimental values. It is observed that the experimental results coincided with ANNs results.
  • No Thumbnail Available
    Item
    The unique relationship between swell percent and swell pressure of compacted clays
    Erzin, Y; Gunes, N
    Expansive soils exhibit high volumetric deformations, posing a serious threat to the stability of structures and foundations. However, measurement of swelling properties is time consuming and requires special and expensive equipment. This study made an attempt to investigate the relationship between these parameters and easily obtained soil properties using various clay mineral mixtures to obtain soils in a wide range of plasticity indices. Free swell percent was correlated to clay percent, water content, dry unit weight, plasticity index, liquidity index and cation exchange capacity using multiple regression analyses. A very high (R = 0.94) fit was also found for a proposed relationship between the percent swell and swell pressure values for samples having a swell pressure a parts per thousand currency sign300 kPa. It is concluded that the proposed equations offer a rapid and inexpensive substitute for laboratory testing of swell percent/swell pressure in the preliminary stages of site investigations.
  • No Thumbnail Available
    Item
    The use of neural networks for the prediction of the settlement of one-way footings on cohesionless soils based on standard penetration test
    Erzin, Y; Gul, T
    In this study, artificial neural networks (ANNs) were used to predict the settlement of one-way footings, without a need to perform any manual work such as using tables or charts. To achieve this, a computer programme was developed in the Matlab programming environment for calculating the settlement of one-way footings from five traditional settlement prediction methods. The footing geometry (length and width), the footing embedment depth, the bulk unit weight of the cohesionless soil, the footing applied pressure, and corrected standard penetration test varied during the settlement analyses, and the settlement value of each one-way footing was calculated for each traditional method by using the written programme. Then, an ANN model was developed for each method to predict the settlement by using the results of the analyses. The settlement values predicted from each ANN model developed were compared with the settlement values calculated from the traditional method. The predicted values were found to be quite close to the calculated values. Additionally, several performance indices such as determination coefficient, variance account for, mean absolute error, root mean square error, and scaled percent error were computed to check the prediction capacity of the ANN models developed. The constructed ANN models have shown high prediction performance based on the performance indices calculated. The results demonstrated that the ANN models developed can be used at the preliminary stage of designing one-way footing on cohesionless soils without a need to perform any manual work such as using tables or charts.
  • No Thumbnail Available
    Item
    The use of neural networks for predicting the factor of safety of soil against liquefaction
    Erzin, Y; Tuskan, Y
    In this paper, the Factor of Safety (FS) values of soil against liquefaction was investigated by means of Artificial Neural Network (ANN) and Multiple Regression (MR). To achieve this, two earthquake parameters, namely earthquake magnitude (M-w) and horizontal peak ground acceleration (a(max)), and six soil properties, namely Standard Penetration Test Number (SPT-N), saturated unit weight (gamma(sat)), natural unit weight (gamma(n)), Fines Content (FC), the depth of Ground Water Level (GWL), and the depth of the soil (d), varied in the liquefaction analysis; then, the FS value was calculated by the simplified method for each case by using the Excel program developed and utilized in the simulation of the feed-forward ANN model with backpropagation algorithm and the MR model. The FS values predicted by both ANN and MR models were compared with those calculated by the simplified method. In addition, five different performance indices were used to evaluate the predictabilities of the models developed. These performance indices indicated that the ANN models were superior to the MR model in terms of predicting the FS value of the soil. (C) 2019 Sharif University of Technology. All rights reserved.
  • No Thumbnail Available
    Item
    The use of neural networks for the prediction of the critical factor of safety of an artificial slope subjected to earthquake forces
    Erzin, Y; Cetin, T
    This study deals with the development of Artificial Neural Network (ANN) and Multiple Regression (MR) models for estimating the critical factor of safety (F-s) value of a typical artificial slope subjected to earthquake forces. To achieve this, while the geometry of the slope and the properties of the man-made soil are kept constant, the natural subsoil properties, namely, cohesion, internal angle of friction, the bulk unit weight of the layer beneath the ground surface and the seismic coefficient, varied during slope stability analyses. Then, the F-s values of this slope were calculated using the simplified Bishop method, and the minimum (critical) F-s value for each case was determined and used in the development of the ANN and MR models. The results obtained from the models were compared with those obtained from the calculations. Moreover, several performance indices, such as determination coefficient, variance account for, mean absolute error and root mean square error, were calculated to check the prediction capacity of the models developed. The obtained indices make it clear that the ANN model has shown a higher prediction performance than the MR model. (C) 2012 Sharif University of Technology. Production and hosting by Elsevier B.V. All rights reserved.
  • No Thumbnail Available
    Item
    The prediction of the critical factor of safety of homogeneous finite slopes subjected to earthquake forces using neural networks and multiple regressions
    Erzin, Y; Cetin, T
    In this study, artificial neural network (ANN) and multiple regression (MR) models were developed to predict the critical factor of safety (F-s) of the homogeneous finite slopes subjected to earthquake forces. To achieve this, the values of F-s in 5184 nos. of homogeneous finite slopes having different slope, soil and earthquake parameters were calculated by using the Simplified Bishop method and the minimum (critical) F-s for each of the case was determined and used in the development of the ANN and MR models. The results obtained from both the models were compared with those obtained from the calculations. It is found that the ANN model exhibits more reliable predictions than the MR model. Moreover, several performance indices such as the determination coefficient, variance account for, mean absolute error, root mean square error, and the scaled percent error were computed. Also, the receiver operating curves were drawn, and the areas under the curves (AUC) were calculated to assess the prediction capacity of the ANN and MR models developed. The performance level attained in the ANN model shows that the ANN model developed can be used for predicting the critical F-s of the homogeneous finite slopes subjected to earthquake forces.
  • No Thumbnail Available
    Item
    The prediction of the critical factor of safety of homogeneous finite slopes using neural networks and multiple regressions
    Erzin, Y; Cetin, T
    This study deals with development of artificial neural network (ANN) and multiple regression (MR) models that can be employed for estimating the critical factor of safety (F-s) value of homogeneous finite slopes. To achieve this, the F-s values of 675 homogenous finite slopes having different soil and slope parameters were calculated by using the simplified Bishop method and the minimum (critical) F-s value for each slope was determined and used in the ANN and MR models. The results obtained from ANN and MR models were compared with those obtained from the calculations. The values predicted from ANN models matched the calculated values much better than those obtained from MR models. Additionally, several performance indices such as determination coefficient (R-2), variance account for (VAF), mean absolute error (MAE), and root mean square error (RMSE) were calculated; the receiver operating curves (ROC) were drawn, and the areas under the curves (AUC) were calculated to assess the prediction capacity of the ANN and MR models. ANN models have shown higher prediction performance than MR models based on the performance indices and the AUC values. The results demonstrated that the ANN models can be used at the preliminary stage of designing homogeneous finite slope. (c) 2012 Elsevier Ltd. All rights reserved.