Fast Extraction of Resonant Frequency of Square Ring Micro-strip antenna using Neural Network Approach

This paper presents an efficient approach based on neural network to design a square ring micro-strip antenna. Traditional techniques used to design a square ring antenna are based on EM field simulations like IE3D which is highly CPU intensive and requires lot of time for simulation. Neural networks can be used to map the complex relationship between physical and electrical parameters of ring antenna in an efficient manner. The model once developed can be used with minimal CPU resources and enables fast extraction of output parameter such as resonant frequency. The typical resonant frequency values are first obtained through IE3D and then from samples obtained from IE3D are used to train the neural network .The results obtained by the use of neural networks have been proved to be faster than comparison with IE3D software.