Design and Analysis of Circular Microstrip Antennas using Artificial Neural Networks

摘要

This paper presents an artificial neural network (ANN) based approach for the design of circular microstrip patch antenna. The difficulty in designing microstrip patch antennas is due to the involvement of large number of physical parameters and hence their associated optimal values. It is indeed very difficult to formulate an exact numerical solution through empirical studies based on practical observations. However, all these solutions are available as approximate models in the form of algebraic equations defining the relationship between different design parameters. In order to circumvent this problem, an alternative solution is achieved using artificial neural networks. In this paper PCCAD software is used to design circular microstrip antenna. A relative performance of the different training algorithms carried out for the design of circular microstrip antenna with particular attention paid to the speed of computation and accuracy. This type of performance comparison has not been attempted so far. Results using ANN are compared with simulated results & theoretical results and are found to be more in agreement with simulated and theoretical results.