Civil Engineering / İnşaat Mühendisliği

Permanent URI for this collectionhttps://hdl.handle.net/11147/13

Browse

Filters

2011 - 20173

Settings

Subject: search.filters.subject.Empirical methods

Search Results

Now showing 1 - 3 of 3
  • Article
    Citation - WoS: 4
    Citation - Scopus: 5
    Use of Principal Component Analysis in Conjunction With Soft Computing Methods for Investigating Total Sediment Load Transferability From Laboratory To Field Scale
    (IWA Publishing, 2014) Tayfur, Gökmen; Karimi, Yashar
    This study quantitatively investigates the generalization from laboratory scale to field scale using the soft computing (expert) and the empirical methods. Principal component analysis is utilized to form the input vector for the expert methods. Five main dimensionless parameters are used in the input vector of artificial neural networks (ANN), calibrated with laboratory data, to predict field total sediment loads. In addition, nonlinear equations are constructed based upon the same dimensionless parameters. The optimal values of the exponents and constants of the equations are obtained by the genetic algorithm (GA) method using the laboratory data. The performance of the sodeveloped ANN and GA based models are compared against the field data and those of the existing empirical methods, namely Bagnold, Ackers and White, and Van Rijn. The results show that ANN outperforms the empirical methods. The results also show that the expert models, calibrated with laboratory data, are capable of predicting field total loads and thus proving their transferability capability. The transferability is also investigated by a newly proposed equation which is based on the Bagnold approach. The optimal values of the coefficients of this equation are obtained by the GA. The performance of the proposed equation is found to be very efficient.
  • Article
    Citation - WoS: 4
    Citation - Scopus: 8
    Investigating a Suitable Empirical Model and Performing Regional Analysis for the Suspended Sediment Load Prediction in Major Rivers of the Aegean Region, Turkey
    (Springer Verlag, 2017) Ülke, Aslı; Tayfur, Gökmen; Özkul, Sevinç
    This study investigates the appropriateness of four major empirical methods [Lane and Kalinske, Einstein, Brooks, Chang—Simons—Richardson] for predicting suspended sediment loads (SSLs) in three major rivers in the Aegean Region, Turkey. The measured data from 1975 to 2005 were used to test performance of the models. It was found that Brooks method was more appropriate, among the others, for predicting suspended sediment loads from each river. The prediction results of Brooks method were further improved by the use of genetic algorithm (GA_Brooks) optimizing a fitting parameter and showing a comparable performance to those of artificial neural networks (ANNs) and neuro-fuzzy (ANFIS) models for the same rivers. GA_Brooks, ANNs, and ANFIS models can be used for predicting loads at a regional scale. The sensitivity analysis results revealed that suspended and bed material particle diameters affect suspended sediment loads significantly.
  • Article
    Citation - WoS: 2
    Citation - Scopus: 2
    Ampirik Yöntemlerle Gediz Nehri için Askıda Katı Madde Yükü Tahmini
    (Turkish Chamber of Civil Engineers, 2011) Ülke, Aslı; Özkul, Sevinç; Tayfur, Gökmen
    It 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.