Abstract: : In this project we have proposed a technique to design and optimize a bow-tie patch antenna with the help of various soft computation techniques such as Adaptive Neuro Fuzzy Inference System (ANFIS), Genetic Algorithm (GA) and a hybrid technique consisting of both ANFIS and GA. The codes for the different soft computation techniquesare developed using the MATLAB software. All results of the antenna are tested on software platform. The software used is IE3D (Integral Equation in Three Dimension) software of Mentor Graphics. The aim of this work is to study and observe resonant frequency, directivity, gain and efficiency obtained by designing the bow-tie patch antenna with the help of the different optimization techniques and to determine which technique gives the most effective antenna. Optimum solutions of various antenna parameters such as length and width are obtained using the soft computation techniques and these are utilized to design the bow-tie antenna using the IE3D software. The design involves a bow-tie antenna being developed on a patch. The patch can take many configurations, the most popular being rectangular and circular configurations. Other configurations are much more complex in design and require heavy numerical computations. In this project a rectangular patch is used. Bow-tie antennas are miniaturized antennas i.e. they are physically small in size, low weight, low cost and they are highly reliable. Also, such a software controlled antenna presents an interesting option for next generation communication.

Keywords: ANFIS, genetic algorithm, resonant frequency; directivity; gain; efficiency; optimum solution, miniaturized antenna.