Tam Derinlikli Esnek Üstyapıların Katman Özelliklerinin Tahmini İçin Lig Şampiyonası Algoritması

This study proposes a backcalculation tool, based on the hybrid use of League Championship Algorithm (LCA) and Artificial Neural Network (ANN), in order to predict the stiffness related layer properties of full-depth asphalt pavements. The proposed algorithm, namely LCA-ANN, is composed of two main parts; (i) an ANN forward response model, which is developed with the nonlinear finite element solution, for computing the surface deflections, and (ii) LCA search algorithm which is employed to search and provide the best set of layer moduli to the ANN model. In order to evaluate the performance of the proposed method, a synthetically generated dataset and real field data are utilized. Moreover, to assess the searching ability of LCA, well-accepted metaheuristic algorithms; Simple Genetic Algorithm (SGA) and Particle Swarm Optimization (PSO) are employed for comparison purposes. Obtained results reveal that the proposed algorithm can predict the layer properties with a low order of error values and enables fast and reliable tool for backcalculation st
Mühendislik Bilimleri ve Tasarım Dergisi


Tam derinlikli esnek üstyapıların destek vektör makineleri yöntemiyle sonlu elemanlar modellemesi
Pekcan, Onur (null; 2018-09-26)
Bu çalışma kapsamında, Destek Vektör Makineleri (DVM) tekniği yardımıyla tam derinlikli esnek üstyapıların sonlu elemanlar yöntemiyle modellenmesinde, güvenilir ve hızlı çalışan bir yaklaşım sunmaktayız. Tam derinlikli esnek üstyapı modeli, doğal zemin ve üzerindeki asfalt kaplamanın eksenel simetrik olarak tasarlanması ile elde edilmektedir. Modellemede asfaltın elastik, doğal zeminin ise doğrusal olmayan (iki taraflı doğrusal) malzeme davranışına sahip olduğu kabul edilmektedir. DVM yöntemi ise, sonlu ele...
A deep learning methodology for the flow field prediction around airfoils
Duru, Cihat; Baran, Özgür Uğraş; Alemdar, Hande; Department of Mechanical Engineering (2021-9-07)
This study aims to predict flow fields around airfoils using a deep learning methodology based on an encoder-decoder convolutional neural network. Neural network training and evaluation are performed from a set of computational fluid dynamics (CFD) solutions of the 2-D flow field around a group of known airfoils at a wide range of angles of attack. Reynolds averaged Navier-Stokes (RANS)-based CFD simulations are performed at a selected Mach number on the transonic regime on high-quality structured computati...
Aerodynamic design and optimization of horizontal axis wind turbines by using bem theory and genetic algorithm
Ceyhan, Özlem; Tuncer, İsmail Hakkı; Department of Aerospace Engineering (2008)
An aerodynamic design and optimization tool for wind turbines is developed by using both Blade Element Momentum (BEM) Theory and Genetic Algorithm. Turbine blades are optimized for the maximum power production for a given wind speed, a rotational speed, a number of blades and a blade radius. The optimization variables are taken as a fixed number of sectional airfoil profiles, chord lengths, and twist angles along the blade span. The airfoil profiles and their aerodynamic data are taken from an airfoil datab...
Physics informed neural networks for computational fluid dynamics
Aygün, Atakan; Karakuş, Ali; Maulik, Romit; Department of Mechanical Engineering (2023-1-17)
In this work, we use physics-informed neural networks (PINN) to model the problems generally used in computational fluid dynamics (CFD). Since PINN does not need any discretization scheme or mesh generation, this approach is easier to implement compared to conventional numerical methods. In the context of CFD problems, the effect of network parameters is shown in the convergence and the accuracy of the solution. The solutions to forward problems are chosen with simple geometries since as the nonlinearity in...
Investigation of variations in performance properties of asphalt concrete using image-based finite element model
Karakaya, Yalçın; Güler, Murat; Department of Civil Engineering (2022-7-20)
The objective of this study is to evaluate variations in performance properties of asphalt concrete using a two-dimensional image-based finite element model. Two different asphalt mixtures are used in both laboratory tests and in FEM analyses representing different conditions. A flatbed scanner is then used to capture cross-sectional images of the samples and various image processing techniques are applied to prepare the images for FEM. A unique image vectorization method has been developed to transform cro...
Citation Formats
O. Pekcan, “Tam Derinlikli Esnek Üstyapıların Katman Özelliklerinin Tahmini İçin Lig Şampiyonası Algoritması,” Mühendislik Bilimleri ve Tasarım Dergisi, pp. 273–284, 2020, Accessed: 00, 2021. [Online]. Available: https://dergipark.org.tr/tr/doi/10.21923/jesd.693743.