Abdulkadir Cevik

Modeling of the uniaxial compressive strength of some clay-bearing rocks using neural network

Uniaxial compressive strength of intact rock is significantly important for engineering geology and geotechnics, because it is an important design parameter for tunnels, rock slopes rock foundations, and it is also used as input parameter in some rock mass classification systems. This paper documents the results of laboratory experiments and numerical simulations (i.e. neural network) conducted to estimate the uniaxial compressive strength of some clay-bearing rocks selected from Turkey. Emphasis was placed on assessing the role of slake durability indices and clay contents. The input variables in developed neural network (NN) model are the origin of rocks, two/four-cycle slake durability indices and clay contents, and the output is uniaxial compressive strength. It is shown that the performance of capacities of proposed NN model is quite satisfactory. However, the NN model including four cycle slake durability index yielded slightly more precise results than that including two cycle slake durability index as input parameter. The paper also presents a comparative study on the accuracy of NN model and genetic programming (GP) in the results.

Accumulated strain prediction of polypropylene modified marshall specimens in repeated creep test using artificial neural networks

This study presents an application of artificial neural networks (ANN) for the prediction of repeated creep test results for polypropylene (PP) modified asphalt mixtures. Polypropylene fibers are used to modify the bituminous binder in order to improve the physical and mechanical properties of the resulting asphaltic mixture. Marshall specimens, fabricated with M-03 type polypropylene fibers at optimum bitumen content were tested using universal testing machine (UTM-5P) in order to determine their rheological/creep behavior under repeated loading. Different load values and loading patterns have been applied to the previously prepared specimens at a predetermined temperature. It has been shown that the addition of polypropylene fibers results in improved Marshall stabilities and decrease in the flow values, providing the increase of the service life of samples under repeated creep testing. The proposed ANN model uses the physical properties of standard Marshall specimens such as polypropylene type, specimen height, unit weight, voids in mineral aggregate, voids filled with asphalt, air voids and repeated creep test properties such as rest period and pulse counts in order to predict the accumulated strain values obtained at the end of mechanical tests. Moreover parametric analyses have been carried out. The results of parametric analyses were used to evaluate the accumulated strain of the Marshall specimens subjected to repeated load creep tests in a quite well manner.

Modelling damping ratio and shear modulus of sand-mica mixtures using genetic programming

This study presents two Genetic Programming (GP) models for damping ratio and shear modulus of sand-mica mixtures based on experimental results. The experimental database used for GP modelling is based on a laboratory study of dynamic properties of saturated coarse rotund sand and mica mixtures with various mix ratios under different effective stresses. In the tests, shear modulus, and damping ratio of the geomaterials have been measured for a strain range of 0.001% up to 0.1% using a Stokoe resonant column testing apparatus. The input variables in the developed NN models are the mica content, effective stress and strain, and the outputs are damping ratio and shear modulus. The performance of accuracies of proposed NN models are quite satisfactory (R2=0.95 for damping ratio and R2=0.98 for shear modulus).

Genetic programming-based attenuation relationship: An application of recent earthquakes in turkey

This study investigates an application of genetic programming (GP) for the prediction of peak ground acceleration (PGA) using strong-ground-motion data from Turkey. The input variables in the developed GP model are the average shear-wave velocity, earthquake source to site distance and earthquake magnitude, and the output is the PGA values. The proposed GP model is based on the most reliable database compiled for earthquakes in Turkey. The results show that the consistency between the observed PGA values and the predicted ones by the GP model yields relatively high correlation coefficients (R^2=0.75). The proposed model is also compared with an existing attenuation relationship and found to be more accurate.

Prediction of Marshall test results for polypropylene modified dense bituminous mixtures using neural networks

This study presents an application of neural networks (NN) for the prediction of Marshall test results for polypropylene (PP) modified asphalt mixtures. PP fibers are used to modify the bituminous binder in order to improve the physical and mechanical properties of the resulting asphaltic mixture. Marshall stability and flow tests were carried out on specimens fabricated with different type of PP fibers and also waste PP at optimum bitumen content. It has been shown that the addition of polypropylene fibers results in the improved Marshall stabilities and Marshall Quotient values, which is a kind of pseudo stiffness. The proposed NN model uses the physical properties of standard Marshall specimens such as PP type, PP percentage, bitumen percentage, specimen height, unit weight, voids in mineral aggregate, voids filled with asphalt and air voids in order to predict the Marshall stability, flow and Marshall Quotient values obtained at the end of mechanical tests. The explicit formulation of stability, flow and Marshall Quotient based on the proposed NN model is also obtained and presented for further use by researchers. Moreover parametric analyses have been carried out. The results of parametric analyses were used to evaluate mechanical properties of the Marshall specimens in a quite well manner.

Modeling strength enhancement of FRP confined concrete cylinders using soft computing

Research highlights? Soft computing techniques for modeling of strength enhancement of FRP confined concrete cylinders. ? Genetic Programming, Stepwise Regression, Neuro-Fuzzy and Neural Networks are used. ? Proposed models are based on experimental results collected from literature. ? Accuracy of the proposed models are quite satisfactory. ? Proposed models are by far more accurate than existing models. This study presents the application of soft computing techniques namely as genetic programming (GP) and stepwise regression (SR), neuro-fuzzy (NF) and neural networks (NN) for modeling of strength enhancement of FRP (fiber-reinforced polymer) confined concrete cylinders. The proposed soft computing models are based on experimental results collected from literature. The accuracy of the proposed soft computing models are quite satisfactory as compared to experimental results. Moreover the results of proposed soft computing formulations are compared with 10 models existing in the literature proposed by various researchers so far and are found to be by far more accurate.

Triaxial compression behavior of sand and tire wastes using neural networks

Tire waste additions to sand enhance the shear strength of sand for embankments. Granular and fiber shape tire wastes and their mixture with sand under drained and undrained conditions were tested in triaxial compression apparatus and modeled using neural networks (NN). In the experimental study, tire crumb and tire buffings inclusions were used at varying contents as soil reinforcement. Both quick tests and consolidated drained (CD) triaxial tests were performed to analyze the effects of tire content, tire shape, and tire aspect ratio on the shear strength of sand. Then, this extensive experimental database obtained in laboratory was used in training, testing, and prediction phases of three neural network-based soil models. The input variables in the developed NN models are tire wastes content, tire wastes type, test type, effective stress, and axial strain, and the output is the deviatoric stress. The accuracy of proposed models seems to be satisfactory. Furthermore, the proposed models are also presented as simple explicit mathematical functions for further use by researchers.

Soft computing based formulation for strength enhancement of CFRP confined concrete cylinders

This study presents the application of soft computing techniques namely as genetic programming (GP) and stepwise regression (SR) for formulation of strength enhancement of carbon-fiber-reinforced polymer (CFRP) confined concrete cylinders. The proposed soft computing based formulations are based on experimental results collected from literature. The accuracy of the proposed GP and SR formulations are quite satisfactory as compared to experimental results. Moreover, the results of proposed soft computing based formulations are compared with 15 existing models proposed by various researchers so far and are found to be more accurate.

Neuro-fuzzy based constitutive modeling of undrained response of Leighton Buzzard Sand mixtures

This study aims to develop neuro-fuzzy (NF) based constitutive model for Leighton Buzzard Sand fraction B and Leighton Buzzard Sand fraction E mixtures using experimental data. The experimental database used for NF modeling is based on a laboratory study of saturated mixtures with various mix ratios under a 100kPa effective stress. Emphasis was placed on assessing the role of fines content in mixture and strain level on the deviatoric stress and pore water pressure generation in a 100mm diameter triaxial testing apparatus. The input variables in the developed rule based NF models are the Leighton Buzzard Sand fraction E content, and strain, and the outputs are deviatoric stress, pore water pressure generation and undrained Youngs modulus. Experimental results show that Leighton Buzzard Sand fraction B and Leighton Buzzard Sand fraction E mixtures exhibits clay-like behavior due to particle-particle effects with the increase in Leighton Buzzard Sand fraction E content. It is also shown that the performance of capacities of proposed NF models are quite satisfactory.

Generating prediction rules for liquefaction through data mining

Prediction of liquefaction is an important subject in geotechnical engineering. Prediction of liquefaction is also a complex problem as it depends on many different physical factors, and the relations between these factors are highly non-linear and complex. Several approaches have been proposed in the literature for modeling and prediction of liquefaction. Most of these approaches are based on classical statistical approaches and neural networks. In this paper a new approach which is based on classification data mining is proposed first time in the literature for liquefaction prediction. The proposed approach is based on extracting accurate classification rules from neural networks via ant colony optimization. The extracted classification rules are in the form of IF-THEN rules which can be easily understood by human. The proposed algorithm is also compared with several other data mining algorithms. It is shown that the proposed algorithm is very effective and accurate in prediction of liquefaction.