Sürdürülebilir Kalkınma Amaçları
Yazarlar
- Adanur, S.(2)
- Altunisik, A.C.(2)
- Bayraktar, Alemdar(2)
- Cakir, Tufan(2)
- Gunaydin, M.(2)
- Kartal, Murat Emre(2)
- Sevim, B.(2)
- Adanur, Süleyman(1)
- Altunişik, Ahmet Can(1)
- Duran, Celal(1)
- Gündogdu, Ali(1)
- Livaoglu, Ramazan(1)
- Sentürk, Hasan Basri(1)
- Sevlm, Bariş(1)
- Çavdar, Ahmet(1)
- Çavdar, Özlem(1)
- Öztürk, Nurcan(1)
- Ünlü, Ramazan(1)
Yayınlar
- MakaleYalnız künye2020An assessment of machine learning models for slump flow and examining redundant features
Ünlü, Ramazan
Over the years, several machine learning approaches have been proposed and utilized to create a prediction model for the high-performance concrete (HPC) slump flow. Despite HPC is a highly complex material, predicting its pattern is a rather ambitious process. Hence, choosing and applying the correct method remain a crucial task. Like some other problems, prediction of HPC slump flow suffers from abnormal attributes which might both have an influence on prediction accuracy and increases variance. In recent years, different studies are proposed to optimize the prediction accuracy for HPC slump flow. However, more state-of-the-art regression algorithms can be implemented to create a better model. This study focuses on several methods with different mathematical backgrounds to get the best possible results. Four well-known algorithms Support Vector Regression, M5P Trees, Random Forest, and MLPReg are implemented with optimum parameters as base learners. Also, redundant features are examined to better understand both how ingredients influence on prediction models and whether possible to achieve acceptable results with a few components. Based on the findings, the MLPReg algorithm with optimum parameters gives better results than others in terms of commonly used statistical error evaluation metrics. Besides, chosen algorithms can give rather accurate results using just a few attributes of a slump flow dataset.
- MakaleYalnız künye2018Modeling of Co(II) adsorption by artificial bee colony and genetic algorithm
Öztürk, Nurcan; Sentürk, Hasan Basri; Gündogdu, Ali; Duran, Celal
In this work, it was investigated the usability of artificial bee colony (ABC) and genetic algorithm (GA) in modeling adsorption of Co(II) onto drinking water treatment sludge (DWTS). DWTS, obtained as inevitable byproduct at the end of drinking water treatment stages, was used as an adsorbent without any physical or chemical pre-treatment in the adsorption experiments. Firstly, DWTS was characterized employing various analytical procedures such as elemental, FT-IR, SEM-EDS, XRD, XRF and TGA/DTA analysis. Then, adsorption experiments were carried out in a batch system and DWTS's Co(II) removal potential was modelled via ABC and GA methods considering the effects of certain experimental parameters (initial pH, contact time, initial Co(II) concentration, DWTS dosage) called as the input parameters. The accuracy of ABC and GA method was determined and these methods were applied to four different functions: quadratic, exponential, linear and power. Some statistical indices (sum square error, root mean square error, mean absolute error, average relative error, and determination coefficient) were used to evaluate the performance of these models. The ABC and GA method with quadratic forms obtained better prediction. As a result, it was shown ABC and GA can be used optimization of the regression function coefficients in modeling adsorption experiments.
- MakaleYalnız künye2017System identification of arch dam model strengthened with CFRP composite materials
Altunisik, A.C.; Gunaydin, M.; Sevim, B.; Adanur, S.
This paper presents the structural identification of an arch dam model for the damaged, repaired and strengthened conditions under different water levels. For this aim, an arch dam-reservoir-foundation model has been constructed. Ambient vibration tests have been performed on the damaged, repaired and strengthened dam models for the empty reservoir (0 cm), 10 cm, 20 cm, 30 cm, 40 cm, 50 cm and full reservoir (60 cm) water levels to illustrate the effects of water levels on the dynamics characteristics. Enhanced Frequency Domain Decomposition Method in the frequency domain has been used to extract the dynamic characteristics. The dynamic characteristics obtained from the damaged, repaired and strengthened dam models show that the natural frequencies and damping ratios are considerably affected from the varying water level. The maximum differences between the frequencies for the empty and full reservoir are obtained as 16%, 33%, and 25% for damaged, repaired and strengthened model respectively. Mode shapes obtained from the all models are not affected by the increasing water level. Also, after the repairing and strengthening implementations, the natural frequencies of the arch dam model increase significantly. After strengthening, between 46-92% and 43-62% recovery in the frequencies are calculated for empty and full reservoir respectively. Apparently, after strengthening implementation, the mode shapes obtained are more acceptable and distinctive compared to those for the damaged model.
- MakaleYalnız künye2017Assessment of effect of material properties on seismic response of a cantilever wall
Cakir, Tufan
Cantilever retaining wall movements generally depend on the intensity and duration of ground motion, the response of the soil underlying the wall, the response of the backfill, the structural rigidity, and soil-structure interaction (SSI). This paper investigates the effect of material properties on seismic response of backfill-cantilever retaining wall-soil/foundation interaction system considering SSI. The material properties varied include the modulus of elasticity, Poisson’s ratio, and mass density of the wall material. A series of nonlinear time history analyses with variation of material properties of the cantilever retaining wall are carried out by using the suggested finite element model (FEM). The backfill and foundation soil are modelled as an elastoplastic medium obeying the Drucker-Prager yield criterion, and the backfill-wall interface behavior is taken into consideration by using interface elements between the wall and soil to allow for de-bonding. The viscous boundary model is used in three dimensions to consider radiational effect of the seismic waves through the soil medium. In the seismic analyses, North-South component of the ground motion recorded during August 17, 1999 Kocaeli Earthquake in Yarimca station is used. Dynamic equations of motions are solved by using Newmark’s direct step-by-step integration method. The response quantities incorporate the lateral displacements of the wall relative to the moving base and the stresses in the wall in all directions. The results show that while the modulus of elasticity has a considerable effect on seismic behavior of cantilever retaining wall, the Poisson’s ratio and mass density of the wall material have negligible effects on seismic response.
- MakaleAçık Erişim2015Static and dynamic responses of Halgavor footbridge using steel and FRP materials
Gunaydin, M.; Adanur, S.; Altunisik, A.C.; Sevim, B.
In recent years, the use of fiber reinforced polymer composites has increased because of their unique features. They have been used widely in the aircraft and space industries, medical and sporting goods and automotive industries. Thanks to their beneficial and various advantages over traditional materials such as high strength, high rigidity, low weight, corrosion resistance, low maintenance cost, aesthetic appearance and easy demountable or moveable construction. In this paper, it is aimed to determine and compare the geometrically nonlinear static and dynamic analysis results of footbridges using steel and glass fiber reinforced polymer composite (GFRP) materials. For this purpose, Halgavor suspension footbridge is selected as numerical examples. The analyses are performed using three identical footbridges, first constructed from steel, second built only with GFRP material and third made of steel-GFRP material, under static and dynamic loadings using finite element method. In the finite element modeling and analyses, SAP2000 program is used. Geometric nonlinearities are taken into consideration in the analysis using P-Delta criterion. The numerical results have indicated that the responses of the three bridges are different and that the response values obtained for the GFRP composite bridge are quite less compared to the steel bridge. It is understood that GFRP material is more useful than the steel for the footbridges.
- MakaleYalnız künye2013Experimental analysis on FEM definition of backfill-rectangular tank-fluid system
Cakir, Tufan; Livaoglu, Ramazan
In the present study, the numerical and experimental investigations were performed on the backfill- exterior wall-fluid interaction systems in case of empty and full tanks. For this, firstly, the non-linear three dimensional (3D) finite element models were developed considering both backfill-wall and fluid-wall interactions, and modal analyses for these systems were carried out in order to acquire modal frequencies and mode shapes by means of ANSYS finite element structural analysis program. Secondly, a series of field tests were fulfilled to define their modal characteristics and to compare the results from proposed approximation in the selected structures. Finally, comparing the theoretical predictions from the finite element models to results from experimental measurements, a close agreement was found between theory and experiment. Thus, it can be easily stated that experimental verifications provide strong support for the finite element models and the proposed procedures themselves are the meritorious approximations to the real problem, and this makes the models appealing for use in further investigations.
- MakaleYalnız künye2010Finite element model updating of an arch type steel laboratory bridge model using semi-rigid connection
Altunişik, Ahmet Can; Bayraktar, Alemdar; Sevlm, Bariş; Kartal, Murat Emre; Adanur, Süleyman
This paper presents finite element analyses, experimental measurements and finite element model updating of an arch type steel laboratory bridge model using semi-rigid connections. The laboratory bridge model is a single span and fixed base structure with a length of 6.1 m and width of 1.1m. The height of the bridge column is 0.85 m and the maximum arch height is 0.95 m. Firstly, a finite element model of the bridge is created in SAP2000 program and analytical dynamic characteristics such as natural frequencies and mode shapes are determined. Then, experimental measurements using ambient vibration tests are performed and dynamic characteristics (natural frequencies, mode shapes and damping ratios) are obtained. Ambient vibration tests are performed under natural excitations such as wind and small impact effects. The Enhanced Frequency Domain Decomposition method in the frequency domain and the Stochastic Subspace Identification method in the time domain are used to extract the dynamic characteristics. Then the finite element model of the bridge is updated using linear elastic rotational springs in the supports and structural element connections to minimize the differences between analytically and experimentally estimated dynamic characteristics. At the end of the study, maximum differences in the natural frequencies are reduced on average from 47% to 2.6%. It is seen that there is a good agreement between analytical and experimental results after finite element model updating. Also, connection percentages of the all structural elements to joints are determined depending on the rotational spring stiffness.
- MakaleYalnız künye2009Stochastic finite element analysis of structural systems with partially restrained connections subjected to seismic loads
Çavdar, Özlem; Bayraktar, Alemdar; Çavdar, Ahmet; Kartal, Murat Emre
The present paper investigates the stochastic seismic responses of steel structure systems with Partially Restrained (PR) connections by using Perturbation based Stochastic Finite Element (PSFEM) method. A stiffness matrix formulation of steel systems with PR connections and PSFEM and MCS formulations of structural systems are given. Based on the formulations, a computer program in FORTRAN language has been developed, and stochastic seismic analyses of steel frame and bridge systems have been performed for different types of connections. The connection parameters, material and geometrical properties are assumed to be random variables in the analyses. The Kocaeli earthquake occurred in 1999 is considered as a ground motion. The connection parameters, material and geometrical properties are considered to be random variables. The efficiency and accuracy of the proposed SFEM algorithm are validated by comparison with results of Monte Carlo simulation (MCS) method.
- DergiGeomechanics and Engineering
- DergiComputers and Concrete