Civil Engineering / İnşaat Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/13
Browse
10 results
Search Results
Article Citation - WoS: 5Citation - Scopus: 6Prediction of Rainfall Runoff-Induced Sediment Load From Bare Land Surfaces by Generalized Regression Neural Network and Empirical Model(Wiley, 2020) Tayfur, Gökmen; Aksoy, Hafzullah; Eriş, EbruBased on three rainfall run-off-induced sediment transport data for bare surface experimental plots, the generalized regression neural network (GRNN) and empirical models were developed to predict sediment load. Rainfall intensity, slope, rainfall duration, soil particle median diameter, clay content of the soil, rill density and soil particle mass density constituted the input variables of the models while sediment load was the target output. The GRNN model was trained and tested. The GRNN model was found successful in predicting sediment load. Sensitivity analysis by the GRNN model revealed that slope and rainfall duration were the most sensitive parameters. In addition to the GRNN model, two empirical models were proposed: (1) in the first empirical model, all the input variables were related to the sediment load, and (2) in the second empirical model, only rainfall intensity, slope and rainfall duration were related to the sediment load. The empirical models were calibrated and validated. At the calibration stage, the coefficients and the exponents of the empirical models were obtained using the genetic algorithm optimization method. The validated empirical models were also applied to two more experimental data sets: (1) one data set was from a field experiment, and (2) one set was from a laboratory experiment. The results indicated the success of the empirical models in predicting sediment load from bare land surfaces.Article Citation - WoS: 1Citation - Scopus: 1Generalized Regression Neural Network and Empirical Models To Predict the Strength of Gypsum Pastes Containing Fly Ash and Blast Furnace Slag(Springer Verlag, 2020) Erdem, Tahir Kemal; Cengiz, Okan; Tayfur, GökmenGypsum is widely used in constructions owing to its easy application, zero shrinkage, and excellent fire resistance. Several parameters can affect the properties of gypsum pastes. To study the strength of the gypsum pastes experimentally by trying all these parameters is time-consuming and costly. Therefore, artificial intelligence methods can be very useful to predict the paste strength, which, in turn, can reduce the number of trial batches. Based on experimental data, the generalized regression neural network (GRNN) and empirical models were developed to predict strength of gypsum pastes containing fly ash (FA) and blast furnace slag (BFS). Gypsum content, pozzolan content, curing temperature, curing duration, and testing age constituted the input variables of the models while the paste strength was the target output. The trained and tested GRNN model was found to be successful in predicting strength. Sensitivity analysis by the GRNN model revealed that the curing duration and temperature were important sensitive parameters. In addition to the GRNN model, empirical models were proposed for the strength prediction. The same input variables formed the input vectors of the empirical models. The same dataset used for the calibration of the GRNN model was employed to establish the empirical models by employing genetic algorithm (GA) method. The empirical models were successfully validated. The GRNN and GA_based empirical models were also tested against the multi-linear regression (MLR) and multi-nonlinear regression (MNLR) models. The results showed the outperformance of the GRNN and the GA_based empirical models over the others.Article Citation - WoS: 66Citation - Scopus: 75Modern Optimization Methods in Water Resources Planning, Engineering and Management(Springer Verlag, 2017) Tayfur, GökmenMathematical (analytical, numerical and optimization) models are employed in many disciplines including the water resources planning, engineering and management. These models can vary from a simple black-box model to a sophisticated distributed physics-based model. Recently, development and employment of modern optimization methods (MOMs) have become popular in the area of mathematical modeling. This paper overviews the MOMs based on the evolutionary search which were developed over mostly the last 30 years. These methods have wide application in practice from finance to engineering and this paper focuses mostly on the applications in the area of water resources planning, engineering and management. Although there are numerous optimization algorithms, the paper outlines the ones that have been widely employed especially in the last three decades; such as the Genetic Algorithm (GA), Ant Colony (AC), Differential Evolution (DE), Particle Swarm (PS), Harmony Search (HS), Genetic Programming (GP), and Gene Expression Programming (GEP). The paper briefly introduces theoretical background of each algorithm and its applications and discusses the merits and, if any, shortcomings. The wide spectrum of applications include, but not limited to, flood control and mitigation, reservoir operation, irrigation, flood routing, river training, flow velocity, rainfall-runoff processes, sediment transport, groundwater management, water quality, hydropower, dispersion, and aquifers.Article Citation - WoS: 27Citation - Scopus: 28Reverse flood routing in natural channels using genetic algorithm(Springer Verlag, 2015) Zucco, Graziano; Tayfur, Gökmen; Moramarco, TommasoEstablishing a clear overview of data discharge availability for water balance modelling in basins is a priority in Europe, and in the particular in the framework of the system of Economic and Environmental Accounts for Water (SEEAW) developed by the EU Directorate-General for the Environment. However, accurate discharge estimation at a river site depends on rating curve reliability usually defined by recording the water level at a gauged section and carrying out streamflow measurements. Local stage monitoring is fairly straightforward and relatively inexpensive compared to the cost to carry out flow velocity measurements which are, in addition, hindered by high flow. Moreover, hydraulic models may not be ideally suitable to serve the purpose of rating curve extension or its development at a river site upstream/downstream where the discharge is known due to their prohibitive requirement of channel cross-section details and roughness information at closer intervals. Likewise, rainfall-runoff transformation might be applied but its accuracy is tightly linked to detailed information in terms of geomorphological characteristics of intermediate basins as well as rainfall pattern data. On this basis, a procedure for reverse flood routing in natural channels is here proposed for three different configurations of hydrometric monitoring of a river reach where lateral flow is significant and no rainfall data are available for the intermediate basin. The first considers only the downstream channel end as a gauged site where discharge and stages are recorded. The second configuration assumes the downstream end as a gauged site but only in terms of stage. The third configuration envisages both channel ends equipped to recording stages. The channel geometry is known only at channel ends. The developed model has basically four components: (1) the inflow hydrograph is expressed by a Pearson Type-III distribution, involving parameters of peak discharge, time to peak, and a shape factor; (2) the basic continuity equation for flow routing written in the characteristic form is employed; (3) the lateral flow is related to stages at channel ends. (4) the relation between local stage and remote discharge as found by Moramarco et al. (2005b) is exploited. The parameters, coefficients and exponents of the model are obtained, for each configuration, using the genetic algorithm method. Three equipped river branches along the Tiber River in central Italy are used to validate the procedure. Analyses are carried out for three significant flood events occurred along the river and where the lateral flow was significant. Results show the good performance of the procedure for all three monitoring configurations. Specifically, the discharge hydrographs assessed at channel ends are found satisfactory both in terms of shape with a Nash-Sutcliffe ranging overall in the interval (0.755–0.972) and in the reproduction of rating curves at channel ends. Finally, by a synthetic test the performance of the developed procedure is compared to that of the hydraulic model coupled with a hydrologic model. Two river reaches are considered, the first along the Tiber River and the second one located in the Rio Grande basin which is a tributary of the Tiber River. Detailed channel geometry data are available for both the river sections. Results showed the effectiveness of the reverse flood routing to reproducing fairly well the hydrographs simulated by the hydraulic model in the three monitoring investigated configurations.Article Citation - WoS: 28Citation - Scopus: 30Principle Component Analysis in Conjuction With Data Driven Methods for Sediment Load Prediction(Springer Verlag, 2013) Tayfur, Gökmen; Karimi, Yashar; Singh, Vijay P.This study investigates sediment load prediction and generalization from laboratory scale to field scale using principle component analysis (PCA) in conjunction with data driven methods of artificial neural networks (ANNs) and genetic algorithms (GAs). Five main dimensionless parameters for total load are identified by using PCA. These parameters are used in the input vector of ANN for predicting total sediment loads. In addition, nonlinear equations are constructed, based upon the same identified dimensionless parameters. The optimal values of exponents and constants of the equations are obtained by the GA method. The performance of the so-developed ANN and GA based methods is evaluated using laboratory and field data. Results show that the expert methods (ANN and GA), calibrated with laboratory data, are capable of predicting total sediment load in field, thus showing their transferability. In addition, this study shows that the expert methods are not transferable for suspended load, perhaps due to insufficient laboratory data. Yet, these methods are able to predict suspended load in field, when trained with respective field data.Article Citation - WoS: 22Citation - Scopus: 29Predicting Mean and Bankfull Discharge From Channel Cross-Sectional Area by Expert and Regression Methods(Springer Verlag, 2011) Tayfur, Gökmen; Singh, Vijay P.This study employed four methods-non-linear regression, fuzzy logic (FL), artificial neural networks (ANNs), and genetic algorithm (GA)-based nonlinear equation-for predicting mean discharge and bank-full discharge from cross-sectional area. The data compiled from the literature were separated into two groups-training (calibration) and testing (verification). Using training data sets, the methods were calibrated to obtain optimal values of the coefficients of the non-linear regression method; optimal number of fuzzy subsets, their base widths and fuzzy rules for the fuzzy method; and the optimal number of neurons in the hidden layer, the learning rate and momentum factor values for the ANN model. The GA-based method employed 100 chromosomes in the initial gene pool, 80% cross over rate and 4% mutation rate in determining the optimal values of the coefficients of the constructed nonlinear equation. The calibrated methods were then applied to the test data sets. The test results showed that the non-linear regression, ANN and GA-based methods were comparable in predicting the mean discharge while the fuzzy method produced high errors and low accuracy. The GA-based method had the highest accuracy of 75%. In terms of predicting bankfull discharge, all methods produced satisfactory results, although the fuzzy method had the lowest accuracy of 33%. The results of sensitivity analysis, which is limited to the GA-based and nonlinear regression methods, showed that the GA-based method calibrated with low bankfull discharge values can be successfully applied to predict high bankfull discharge values. This has important implications for predicting bankfull rates at ungauged sites. On the other hand, the sensitivity analysis results also showed that both the non-linear regression and GA-based methods have poor extrapolation capability for predicting mean discharge data.Article Citation - WoS: 2Citation - Scopus: 2Ampirik Yöntemlerle Gediz Nehri için Askıda Katı Madde Yükü Tahmini(Turkish Chamber of Civil Engineers, 2011) Ülke, Aslı; Özkul, Sevinç; Tayfur, GökmenIt is essential to predict suspended sediment load for understanding river morphology, design of dams, water supply problems, management of reservoirs and determination of pollution levels in rivers. The suspended sediment load can be determined by means of several methods such as direct measurements at the sediment gauging stations, sediment rating curve, son modeling methods, and empirical methods which are based on experimental works. The objective of this study is first to determine the best empirical method for Gediz river and then to improve the determined method by genetic algorithm (GA). It is seen that the GA improved Brooks method can be used for Gediz River Basin. In addition, this method was compared with other soft computing (ANN, ANFIS) methods and its performance is found to be as good as them.Article Citation - WoS: 24Citation - Scopus: 24GA-optimized model predicts dispersion coefficient in natural channels(IWA Publishing, 2009) Tayfur, GökmenModels whose parameters were optimized by genetic algorithm (GA) were developed to predict the longitudinal dispersion coefficient in natural channels. Following the existing equations in the literature, ten different linear and nonlinear models were first constructed. The models relate the dispersion coefficient to flow and channel characteristics. The GA model was then employed to find the optimal values of the constructed model parameters by minimizing the mean absolute error function (objective function). The GA model utilized an 80% cross-over rate and 4% mutation rate. It started each computation with a population of 100 chromosomes in the gene pool. For each model, while minimizing the objective function, the values of the model parameters were constrained between [-10, +10] at each iteration. The optimal values of the model parameters were obtained using a calibration set of 54 out of 80 sets of measured data. The minimum error was obtained for the case where the model was a linear equation relating dispersion coefficient to flow discharge. The model performance was then satisfactorily tested against the remaining 26 measured validation datasets. It performed better than the existing equations. it yielded minimum errors of MAE = 21.4m2/s (mean absolute error) and RMSE = 28.5m2/s (root mean-squares error) and a maximum accuracy rate of 81%. © IWA Publishing 2009.Article Citation - WoS: 135Citation - Scopus: 157The Use of Ga-Anns in the Modelling of Compressive Strength of Cement Mortar(Elsevier Ltd., 2003) Akkurt, Sedat; Özdemir, Serhan; Tayfur, Gökmen; Akyol, BurakIn this paper, results of a project aimed at modelling the compressive strength of cement mortar under standard curing conditions are reported. Plant data were collected for 6 months for the chemical and physical properties of the cement that were used in model construction and testing. The training and testing data were separated from the complete original data set by the use of genetic algorithms (GAs). A GA-artificial neural network (ANN) model based on the training data of the cement strength was created. Testing of the model was also done within low average error levels (2.24%). The model was subjected to sensitivity analysis to predict the response of the system to different values of the factors affecting the strength. The plots obtained after sensitivity analysis indicated that increasing the amount of C3S, SO3 and surface area led to increased strength within the limits of the model. C2S decreased the strength whereas C3A decreased or increased the strength depending on the SO3 level. Because of the limited data range used for training, the prediction results were good only within the same range. The utility of the model is in the potential ability to control processing parameters to yield the desired strength levels and in providing information regarding the most favourable experimental conditions to obtain maximum compressive strength.Conference Object Citation - WoS: 1Citation - Scopus: 6Genetic Algorithm-Artificial Neural Network Model for the Prediction of Germanium Recovery From Zinc Plant Residues(Taylor and Francis Ltd., 2002) Akkurt, Sedat; Özdemir, Serhan; Tayfur, GökmenA multi-layer, feed-forward, back-propagation learning algorithm was used as an artificial neural network (ANN) tool to predict the extraction of germanium from zinc plant residues by sulphuric acid leaching. A genetic algorithm (GA) was used for the selection of training and testing data and a GA-ANN model of the germanium leaching system was created on the basis of the training data. Testing of the model yielded good error levels (r2 = 0.95). The model was employed to predict the response of the system to different values of the factors that affect the recovery of germanium and the results facilitate selection of the experimental conditions in which the optimum recovery will be achieved.