Civil Engineering / İnşaat Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/13
Browse
3 results
Search Results
Article Citation - WoS: 5Citation - Scopus: 5Developing Predictive Equations for Water Capturing Performance and Sediment Release Efficiency for Coanda Intakes Using Artificial Intelligence Methods(MDPI, 2022) Hazar, Oğuz; Tayfur, Gökmen; Elçi, Şebnem; Singh, Vijay P.Estimation of withdrawal water and filtered sediment amounts are important to obtain maximum efficiency from an intake structure. The purpose of this study is to develop empirical equations to predict Water Capturing Performance (WCP) and Sediment Release Efficiency (SRE) for Coanda type intakes. These equations were developed using 216 sets of experimental data. Intakes were tested under six different slopes, six screens, and three water discharges. In SRE experiments, sediment concentration was kept constant. Dimensionless parameters were first developed and then subjected to multicollinearity analysis. Then, nonlinear equations were proposed whose exponents and coefficients were obtained using the Genetic Algorithm method. The equations were calibrated and validated with 70 and 30% of the data, respectively. The validation results revealed that the empirical equations produced low MAE and RMSE and high R2 values for both the WCP and the SRE. Results showed outperformance of the empirical equations against those of MNLR. Sensitivity analysis carried out by the ANNs revealed that the geometric parameters of the intake were comparably more sensitive than the flow characteristics.Article Citation - WoS: 6Citation - Scopus: 6Calibration and Verification of Century Based Wave Climate Data Record Along the Turkish Coasts Using Satellite Altimeter Data(Elsevier Ltd., 2020) Özbahçeci, Bergüzar; Turgut, Ahmet Rıza; Bozoklu, Ahmet; Abdalla, S.In order to produce consistent reanalysis of the climate system, ECMWF (The European Centre for Medium-Range Weather Forecasts) has produced firstly an uncoupled atmospheric reanalysis ERA-20C, and then a coupled climate reanalysis, called CERA-20C, which covers the period January 1900 to December 2010. Both data sets are available at 3-hour time increments. Such a century long data can be an alternative to calculate the extreme waves corresponding to low probability of occurrences without extrapolation of extreme value statistics’ results which may contribute to the error in the estimation of design waves in case of small number of wave data. In this study, main purpose is to calibrate and verify the century-based wave data in order to derive the longest and the consistent wave data along the Turkish coasts as a first time to be used in the extreme wave analysis. For this purpose, first of all, significant wave height data of ERA-20C and CERA-20C are compared by using ENVISAT data over the whole Black Sea for 2007–2008 as a pilot study. Comparison results show that both datasets give similar results but CERA-20C seems to be better in terms of statistical error measures. Then CERA-20C significant wave height data are calibrated using satellite Radar Altimeter data set. Jason family of satellites (TOPEX, Jason-1 and 2) and Envisat family of satellites (ERS-2 and Envisat) are inter-calibrated to get the consistent satellite data sets with a total duration of 18 years (1995–2012) for Envisat family and 26 years (1992–2017) for Jason family in order to be used in calibration of CERA-20C wave height. The mean wave period is also estimated from RA backscatter coefficients (Ku and C bands) and the significant wave height by using Artificial Neural Network Method. Then the estimated mean wave periods are used for the calibration of CERA-20C wave period. Calibrated CERA-20C data are compared with in-situ measurements for the verification purposes. Results of verification study show that the calibrated CERA-20C wave data agree well with the in-situ measurements in terms of Quantile-Quantile analysis with lower deviations from y = x line and capture the largest sea states. In fact, CERA-20C, century-based wave data become appropriate to determine the extreme waves to be used in the design of coastal structures along the Turkish coasts. © 2020 COSPARArticle 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.