Yazar "Dundar, O." seçeneğine göre listele
Listeleniyor 1 - 3 / 3
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Calculation of Circular Microstrip Antenna Parameters with a Single Artificial Neural Network Model(ELECTROMAGNETICS ACAD, 2012) Gultekin, S. S.; Uzer, D.; Dundar, O.A model for the design of circular microstrip antennas, based on Artificial Neural Networks, is presented. The multiple output design parameters are calculated by using a neural network. This neural model is simple and useful for the computer-aided design (CAD) of microstrip antennas. A distinct advantage of neural computation is that, after proper training, a neural network completely bypasses the repeated use of complex iterative processes for new cases presented to it. For engineering applications, this simple model is very usable. Thus the neural model given in this work can also be used for many engineering applications and purposes. In this study, for this neural network model, patch radius, radiation resistance, directivity, total quality factor, bandwidth, efficiency and gain are calculated as output parameters against input parameters as dielectric constant, resonant frequency, dielectric substrate thickness and tangent loss. Extended Delta-Bar-Delta training algorithm by Multi layer Perceptron structure that used popular in literature and gives good approaches is used for training the network. The design results obtained by using the neural model are in very good agreement with the results available in the literature.Öğe Effects of Microstrip Feed Line Width on 1 x 4 Rectangular Microstrip Antenna Array Electrical Parameters and Estimation with Artificial Neural Networks(ELECTROMAGNETICS ACAD, 2012) Dundar, O.; Uzer, D.; Gultekin, S. S.; Bayrak, M.In this study, 1 x 4 rectangular microstrip array antennas are designed at 16 GHz resonant frequency for KU Band usage on Duroid 5880 substrate that has a thickness of 0.254 mm and a dielectric constant of 2.2. Designs are simulated using HFSS v12. At these designs, by changing the feed line widths systematically, for each antenna, electrical parameters like Sit response, directivity, gain, radiation efficiency etc. are investigated for 26 array antennas in simulation media. Also, directivity and gain values are predicted with an Artificial Neural Network model. The network has four inputs as dielectric substrate thickness, resonant frequency and dielectric constant of the substrate and three outputs as directivity, gain and radiation efficiency. Multi layer perceptron structure for Artificial Neural Network model and Levenberg-Marquart learning algorithm for training the network are used. The network model is trained with 20 of 26 design data and is tested with the rest 6 ones. It is seen that the results from simulations and the neural network model are compatible with similar studies in the literature.Öğe Estimation and Design of U-slot Physical Patch Parameters with Artificial Neural Networks(ELECTROMAGNETICS ACAD, 2012) Uzer, D.; Gultekin, S. S.; Dundar, O.In this study, physical U slot parameters of rectangular microstrip patch antennas as vertical and horizontal slot lengths and widths with the patch lengths and widths are determined by the help of Artificial Neural Networks. The aim of the study is calculation of physical U slot patch parameters without any mathematical expressions or long and complex numeric calculations with a neural network model. Experimental results in the literature are used as the training data for the network by using Gradient Descent with Adaptive Learning Rate Back Propagation learning algorithm. The resonant frequency, dielectric constant of the substrate and the dielectric substrate thickness values are the inputs of the neural network and the patch length, patch width, the lengths and widths of the vertical and horizontal slots are the network outputs. The test output data of the network are used for simulations and the results are confirmed by these simulations. S-11 responses, simulation frequency, impedance bandwidth, directivity, gain and radiation efficiency values of the antennas are investigated by HFSS. Simulation results are compatible with test outputs. The high training success of the network and R-2 values very close to 1 show that physical patch parameters of U-slot rectangular microstrip antennas can be calculated with this Artificial Neural Network model with high accuracy.
