Civil Engineering / İnşaat Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/13
Browse
2 results
Search Results
Article Citation - WoS: 8Citation - Scopus: 9Empirical, Numerical, and Soft Modelling Approaches for Non-Cohesive Sediment Transport(Springer, 2021) Tayfur, GökmenThis paper reviews the modelling approaches and outstanding issues with regard to non-cohesive sediment transport which has been experimentally and numerically studied for many decades owing to its importance to hydraulic structures, morphology and related areas. About 311 papers are reviewed that included laboratory experiments, field observations, and analytical and numerical modelling studies. The reviewed papers cover the period 1938-2020. Of 311, 95 papers are included in this paper. The modeling approaches include empirical, physics-based, spatially averaged, and soft methods. The empirical models have oversimplified the process while the physics-based models are indispensable when the detailed analysis is required. On the other hand, when the objective is to obtain cumulative sediment loads, it would be advantageous to employ the spatial averaging modelling and/or the soft computing methods due to less computational burden and data requirements. The outstanding issues are related to the particle fall velocity, particle velocity, incipient motion, and transport function that require further experimental investigations especially for unsteady non-uniform transport processes.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.