18-07-2012, 11:18 AM
Using ANN Design of Elliptical Microstrip Patch Antenna
Using-ANN-Design-of-Elliptical-Microstrip-Patch-Antenna-for-Circular-Polarization.pdf (Size: 274.29 KB / Downloads: 46)
INTRODUCTION
Microstrip patch antennas are low profile,
conformable to planar and non-planar surfaces, and
can be easily fabricated using printed circuit board
technology. They are also mechanically robust when
mounted on rigid surfaces, and compatible with
Monolithic microwave integrated circuit (MMIC)
designs. These patch antennas are used for highperformance
spacecraft, aircraft, missile and satellite
applications, where size, weight, cost, performance,
ease of installation, and aerodynamic profile are
constraints When a particular patch shape and excited
mode are selected they are very versatile in terms of
resonant frequency, polarization, radiation pattern, and
impedance.
THEORY
Elliptical patch antenna is shown in Fig. 1, where a is
the semi major axis, b is the semi minor axis and aeff is
the effective semi-major axis. The feed position is
located along the 45º line between the major and
minor axis of the elliptical patch. The radiated fields
cause two modes that are perpendicular to each other
and have equal amplitude, but are 900 out of phase. An
elliptical patch antenna with optimum dimensions acts
as a Circular Polarized wave radiator [2].
ANN MODELING
FFBPNN has three layers of neurons, namely input,
hidden and output, which are fully interconnected as
shown in Fig. 2. The input layer consists of just the
inputs to the network. The number of nodes, n is equal
to the dimension of input vector X = (x1, x2…..,xn).
Then follow a hidden layer, which consist of any
number of neuron. Each neuron performs a weighted
summation of the inputs, which then passes a
nonlinear activation function σ, also called the neuron
function.
CONCLUSION
The results obtained by using FFBPNN for elliptical
microstrip patch antennas are in good agreement with
available targeted results. The proposed network
requires less training time and is more accurate in
prediction. Using these FFBPNN models, various
possible dimensions can be obtained to achieve high
bandwidth and single feed circular polarization. ANN
models are simple, easy to apply and very useful for
antenna engineers to predict both patch dimensions
and resonant frequency.