Modeling the mutual coupling of circular DRA MIMO array using Artificial Neural Networks

Main Article Content

K Jagadeesh Babu
Dr. K Sri Ramakrishna,Dr.L Pratap Reddy, J Lakshmi Narayana


A circular Dielectric Resonator Antenna (DRA), operating at the resonant frequencies 7.4GHz and 8GHz is developed for a two element Multiple Input Multiple Output (MIMO) system. The proposed antenna gives an impedance bandwidth of 20%, which is suitable for UWB applications. The mutual coupling between the two antennas is modelled by using the computational tool, Artificial Neural Networks. The neural structure is trained by using different ANN algorithms and a comparative study is made between them. It is shown that, Quasi Newton and Quasi Newton MLP algorithms are better in terms of training, testing errors and correlation coefficient. The mutual coupling is shown to reduce as the separation between the two antennas is increased. The neural network generated data and EM simulator data are compared for a separation of 10mm and a small variation of 1 dB in the mutual coupling is observed.



Keywords: DRAs, MIMO systems, Artificial Neural Networks, mutual coupling, impedance bandwidth.


Download data is not yet available.

Article Details