Hybridization strategy for microstrip antenna optimization

In the exploding growth of radio mobile and wireless communication applications, microstrip antennas with its advantages of low cost and flexible fabrications, emerge as the most suitable candidate. The direct antenna synthesis could, however do not result in the optimal antenna configuration, and therefore a possible alternative is considering the problem of optimizing the antenna as a system of uncertainty, in which each set of geometrical parameters returns a totally different response; the best set, i.e. the one that gives the best antenna performances, can be obtained using global optimizers, as evolutionary algorithms. The main drawback of this approach is that it is really time and memory consuming. In this article, a technique based on the hybridization between Particle Swarm Optimization (PSO) and Artificial Neural Network (ANN)is introduced with the aim of reducing this nimerical cost and implemented to optimize a dual-annular ring proximity coupled feed antenna.