Marija Milijic

Modeling of patch antennas using neural networks

In this paper patch antennas are modeled using neural model based on multi-layer perceptrons (MLP) network. Neural model is trained by data, which are obtained by electromagnetic simulation of antennas using HFSS 9.0 software. This model has four input parameters: patch antenna length L, patch antenna width W, deep of patch antenna slot l and width of patch antenna slot s and it enables quick and correct calculation of resonant frequency f/sub r/ and minimum value of S/sub 11/ parameter (S/sub 11min/).

Near-Earth Propagation Loss Prediction in Open Rural Environment using Hybrid Empirical Neural Model

New hybrid empirical neural (HEN) model for prediction EM field level of wireless communication transmitter in frequency range 150-1500 MHz is presented in this paper. Previous empirical Okumura-Hata model, which has been very often used, does not consider all influences of environment that signal goes throughout. Therefore, the results obtained by this model can disagree with the measured results. Considering Okumura-Hata model as approximate empirical knowledge holder and connecting it with the artificial neural network, in this paper we will realize the HEN model whose estimated results are more closed to measured results than Okumura-Hata results.

Side lobe suppression of printed antenna array with perpendicular reflector

Side lobe suppression of printed antenna arrays with perpendicular reflector has been analyzed in this article. The arrays are with pentagonal dipoles as radiating elements operating at a second resonance. The used distribution is chosen to enable high side lobe suppressions bigger than 41.5 dB at the frequency of 12 GHz. The feeding network in symmetrical (balanced) microstrip technique with impedance transformers is presented too. The antenna arrays with the high side lobe suppression are very sensitive in small deviation of distribution coefficients from ideal that can results in decreasing SLS values. Therefore, the optimal feeding network with minimal departure from determined distribution is investigated.

Design, Realization, and Measurements of a Corner Reflector Printed Antenna Array With Cosecant Squared-Shaped Beam Pattern

The detailed research, full development, and experimental realization of a new printed antenna array with cosecant squared-shaped beam pattern are presented. Some advantages of proposed antenna, as compared to previously realized microstrip cosecant-squared pattern antennas, are pointed out. The suggested antenna, which targets X frequency range, has significantly better bandwidth characteristics thanks to its symmetrical radiating elements of pentagonal shape. The symmetrical feeding network of impedance transformers provides necessary amplitudes and phases distributions obtained by Orchard Elliotts methods and genetic algorithm. Furthermore, it is on the same substrate as antenna, making entire concept simple, easy, and cheap for realization. Moreover, the antenna is in a corner reflector, which enables achieving relatively high gain. The proposed antenna is validated by simulations and measurements. The measured radiation pattern barely varies from theoretical radiation pattern. Realized antenna has gain above 15 dBi and sidelobe suppression greater than 20 dB at the center frequency of 10 GHz.

ANN based inverse modeling of RF MEMS capacitive switches

RF MEMS switches have been efficiently applied in various applications in communication systems. Therefore, there is a need for reliable and accurate models of RF MEMS switches. Artificial neural networks (ANNs) have been appeared as very efficient alternative to time consuming full-wave and/or mechanical simulations of RF MEMS devices. However, to optimize the switch geometry it is usually necessary to perform certain optimization procedures. In this paper the development of ANN based procedures to be used as a feed-forward tool for determination of the switch geometrical parameters avoiding optimizations is proposed. The proposed procedure is developed for determination of the length of the bridge fingered part of a capacitive switch to achieve the desired electrical resonance frequency or the necessary actuation voltage.

Artificial neural networks for efficient RF MEMS modeling

In this contribution we will show how artificial neural networks can be efficiently used to build models of RF MEMS components or to optimize them without enhanced numerical efforts. The method is especially interesting for designers and technologists, who want to modify or optimize switch parameters for a fixed technology without using heavy simulation tools. As examples the fast and accurate calculation of scattering parameters for an ohmic switch dependent on 4 different geometrical dimensions over frequency is shown. The second example is the derivation of some lateral dimensions for the resonant frequency of a capacitive switch without using optimization routines.

Efficient model of slotted patch antenna based on neural networks

This paper introduces the efficient neural networks model of slotted patch antenna. The model calculates the resonant frequency and minimum value of S 11 parameters considering both antenna dimensions and dielectric characteristics. The proposed neural model has similar accuracy as detailed electromagnetic (EM) methods while its simulation speed is significantly greater.

Hybrid empirical-neural approach in modeling EM propagation in urban environment with foliage areas

The hybrid empirical neural (HEN) approach for modeling EM propagation in urban environment is presented in this paper. Proposed model is based on connection between artificial neural network and Okamura-Hata model. It predicts electric field strength of RF transmitter in frequency range 150-1500 MHz considering antenna frequency, transmitter antenna height, distance between antenna and receiver, time variability, characteristics of foliage areas and characteristics of buildings in urban environment that EM wave goes throughout. The comparison between this model and multilayered perceptron (MLP) model is also presented in the paper. HEN model is connected with GIS-MW GeoRef software module in order to display predicted results in application geo-referencing space.

Hybrid Empirical-Neural Model of Microwave Slotted Patch Antennas

This paper presents a new hybrid empirical-neural model (HEN) for slotted patch antenna modeling. Unlike the model based on a classical multi-layer perceptron (MLP) network, the proposed HEN model includes an existing partial knowledge about both the resonant frequency fr behavior and the minimum value of S11 parameter (s11min) behavior of patch antenna, yielding more accurate determination of these patch antenna parameters

Feeding structure influence on side lobe suppression of printed antenna array with parallel reflector

The paper investigates the feeding structures for printed antenna arrays with parallel reflector and their influences on antenna parameters. Two printed antenna arrays are presented. The first consists of ten series fed symmetrical dipoles with tapered impedances. The second is the array of eight symmetrical dipoles that are fed by a tapered distribution. The feeding structures for both antennas are realized in symmetrical (balanced) microstrip technique eliminating surface wave effect. However, a parasitic radiation from a feeding network cannot be avoided and it affects antenna performances, especially side lobe suppression. This influence is the most obvious for the antenna with parallel reflector where there is not isolation between array and feeding structure.