This paper presents the general design of microstrip antennas using Artificial Neural Networks (ANN) for rectangular patch geometry. The design consists of synthesis as the forward side and analysis as the reverse side of the problem. In this work, the neural network is employed as a tool in the design of microstrip antennas. The neural network training algorithms are used for training the samples to minimize the error and to obtain the geometric dimensions of patch antenna with high accuracy for selective band of frequencies using reverse modeling.

To meet the requirements of high performance spacecraft, aircraft, satellite and cellular mobile communication, microstrip antennas are used [1]. Often microstrip antennas are referred to as patch antennas because the radiating elements are photo etched on the dielectric substrate. The new radiating patch may be of any shape like square, rectangular, circular, elliptical, triangular. In [2], rectangular microstrip patch antennas are considered where patch dimensions of rectangular microstrip antennas are designed for the pattern to be normal to the patch. Because of sharp bandwidths and effectively operation in the vicinity of resonant frequency, the choice of the patch dimensions for the specified resonant frequency is very important [3]. Artificial Neural Network (ANN) models have been built for the analysis of microstrip antennas in various forms such as rectangular, circular and equilateral triangle patch antennas [4-7]. The analysis is defined to obtain resonant frequency for a given dielectric material and geometric structure. However, the corresponding synthesis ANN model is built to obtain patch dimensions of rectangular microstrip antennas (W, L) as the function of input variables, which are the height of the dielectric substrate (h), dielectric constants of the dielectric material (ε_r, ε_y), and the resonant frequency (f_r). This synthesis problem is solved using the electromagnetic formulae of the microstrip antennas [8-11]. Emphasis is given on the resonant frequency of the patch antenna and the conditions for radiation efficiency. Using reverse modeling, an analysis ANN is built to find out the resonant frequency (upper and lower) for a given rectangular microstrip antenna system.

The forward and the reverse sides of this design problem are defined as black-ANN boxes, then the electromagnetic background is briefly summarized for building the synthesis ANN model and is reversed for the analysis purpose of the given antenna system whose results are compared with existing designs. The rectangular microstrip antennas are made of rectangular patches with width, W, and length, L, over a ground plane with a substrate thickness h and dielectric constants ε_r, ε_y, as given in Figure 1. Dielectric constants used are in the range 2.2 ≤ ε_r ≤ 10. However, the most desirable are the dielectric constants at the lower end of this range, together with the thick substrates, because they provide better efficiency and larger bandwidth, but at the expense of larger element size [12-13].

Science and Technology Journal, Microstrip Patch Antennas, Neural Network, Artificial Neural Networks, Microstrip Antennas, Reverse Modeling, Black-ANN Boxes, Neural Network Applications, Multilayer Perceptron Models, Electromagnetic Simulator, Back Propagation Algorithm.