Hybrid neural network optimization for feed point determination in antenna design

In this paper, coaxially feed rectangular microstrip antenna is designed for WIFI communication in accordance with IEEE 802.11a standard between 5.15 GHz and 5.725 GHz. Feeding position of coaxial probe significantly affected antenna characteristics. Optimum feeding point should be selected in 2-D patch plane on the purpose of better antenna characteristics. The model is used to solve the optimization problem. It has three input variables which are antenna parameters as resonance frequency, bandwidth and return loss; on the otherhand, two output such as x and y coordinates of feeding position. Also, error function is updated by proposed artificial intelligence algorithms. Unlike conventional methods, contemporary artificial intelligent algorithms have been proposed for the antenna design. Genetic Algorithm (GA), Spider Monkey Optimization (SMO) and Grey Wolf Optimizer (GWO) are preferred for optimization. According to comparison of these results, optimal antenna for WIFI Protocol is designed. Copyright held by the author(s).