Yazar "Taskiran, T." seçeneğine göre listele
Listeleniyor 1 - 4 / 4
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Adaptive neuro-fuzzy modeling for the swelling potential of compacted soils(Springer, 2009) Kayadelen, C.; Taskiran, T.; Gunaydin, O.; Fener, M.This paper aims to present the usability of an adaptive neuro fuzzy inference system (ANFIS) for the prediction swelling potential of the compacted soils that are important materials for geotechnical purposes such as engineered barriers for municipal solid waste, earth dams, embankment and roads. In this study the swelling potential that is also one of significant parameters for compacted soils was modeled by ANFIS. For the training and testing of ANFIS model, data sets were collected from the tests performed on compacted soils for different geotechnical application in Nigde. Four parameters such as coarse-grained fraction ratio (CG), fine-grained fraction ratio (FG), plasticity index (PI) and maximum dry density (MDD) were presented to ANFIS model as inputs. The results obtained from the ANFIS models were validated with the data sets which are not used for the training stage. The analyses revealed that the predictions from ANFIS model are in sufficient agreement with test results.Öğe Critical-state parameters of an unsaturated residual clayey soil from Turkey(Elsevier Science Bv, 2007) Kayadelen, C.; Sivrikaya, O.; Taskiran, T.; Guneyli, H.This paper deals with the evaluation of the critical-state parameters with respect to the matric suction for saturated and unsaturated undisturbed residual clayey soils from Turkey. In order to conduct the unsaturated triaxial compression testing procedures a conventional triaxial compression apparatus was redesigned. The data for critical-state conditions from these tests are presented with respect to matric suction, based on the critical-state parameters of M, q(0), Gamma, lambda, which is commonly proposed by many authors. The critical state of the unsaturated samples is compared with that of the saturated samples. This experimental study has demonstrated that matric suction has no influence on parameters of M and lambda. The parameters of M and lambda are approximately 0.85 and 0.074 respectively for saturated and unsaturated conditions. The relationships between matric suction (u(a)-u(w)) and the intercepts q(0) and Gamma have been observed as nonlinear, and thus they can be defined as a function of matric suction (u(a)-u(w)). Furthermore, a method is developed to predict the intercepts q(0) according to matric suction for unsaturated clayey soils. (c) 2007 Elsevier B.V. All rights reserved.Öğe Influence of matric suction on shear strength behavior of a residual clayey soil(Springer, 2007) Kayadelen, C.; Tekinsoy, M. A.; Taskiran, T.In this paper, the shear strength with respect to the matric suction of unsaturated soils was studied. For this purpose, unsaturated triaxial testing procedures were applied to the undisturbed residual soil specimens. An apparatus for performing triaxial tests was designed and constructed. In the tests, matric suction was controlled by using the axis translation technique, and pore water volume changes were measured by means of a volume change transducer with 10(-8) m(3) sensitivity. The test results indicated that the matric suction contributes to the shear strength of unsaturated soil specimens, and this contribution called suction strength varies non-linearly with respect to the matric suction. The logarithmic model needing to know the air-entry value and the internal friction angle of a soil specimen for prediction of the suction strength were presented and compared with the test results. It was found that suction strength values predicted from the proposed model were in satisfactory agreement with the experimental results.Öğe Prediction of California bearing ratio (CBR) of fine grained soils by AI methods(Elsevier Sci Ltd, 2010) Taskiran, T.Advances in field of artificial intelligence (AI) offers opportunities of utilizing new algorithms and models that enable researchers to solve the most complex systems. As in other engineering fields, AI methods have widely been used in geotechnical engineering. Unlikely, there seems quite insufficient number of research related to the use of AI methods for the estimation of California bearing ratio (CBR). There were actually some attempts to develop prediction models for CBR, but most of these models were essentially statistical correlations. Nevertheless, many of these statistical correlation equations generally produce unsatisfactory CBR values. However, this paper is likely one of the very first research which aims to investigate the applicability of AI methods for prediction of CBR. In this context, artificial neural network (ANN) and gene expression programming (GEP) were applied for the prediction of CBR of fine grained soils from Southeast Anatolia Region/Turkey. Using CBR test data of fine grained soils, some proper models are successfully developed. The results have shown that the both ANN and GEP are found to be able to learn the relation between CBR and basic soil properties. Additionally, sensitivity analysis is performed and it is found that maximum dry unit weight (gamma(d)) is the most effective parameter on CBR among the others such as plasticity index (PI), optimum moisture content (W-opt), sand content (S), clay + silt content (C + S), liquid limit (LL) and gravel content (G) respectively. (C) 2010 Elsevier Ltd. All rights reserved.
