Artificial Neural Network based Parameter Estimation and Design Optimization of Loop Antenna

Artificial Neural Network (ANN)s are best suited for prediction and optimization problems. Trained ANNs have found wide spread acceptance in several antenna design systems. Four parameters namely antenna radiation resistance, loss resistance, efficiency, and inductance can be used to design an antenna layout though there are several other parameters available. An ANN can be trained to provide the best and worst case precisions of an antenna design problem defined by these four parameters. This work describes the use of an ANN to generate the four mentioned parameters for a loop antenna for the specified frequency range. It also provides insights to the prediction of best and worst-case design problems observed in applications and thereby formulate a model for physical layout design of a loop antenna.

Authors:

• Kumaresh Sarmah
• Kandarpa Kumar Sarma

Keywords:

• MLP
• ANN
• parameter
• prediction
• optimization.

References:

[1] S. Haykin. "Neural Networks: A Comprehensive Foundation". Pearson
Education, 2nd Ed., New Delhi, 2003.
[2] V. R. Gupta and N. Gupta. "An Artificial Neural Network Model for Feed
Position of the Microstrip Antenna", Electronika Ir Elektrotechnika,
2005.
[3] R. K. Mishra, and A. Patnaik, . "Neural Network Based CAD Model for
the Design of Square-Patch Antenna". IEEE Transactions on Antenna
And Propagation, December, 1998.
[4] K. Siakavara . "Artificial Neural Network Employment in the Design of
Multilayred Microstrip Antenna with Specified Frequency Operation",
PIERS Proceedings, pp. 27 − 30, Prague, August, 2007.
[5] A. A. Eldek . " Design Of Double Dipole Antenna With Enhanced
Usable Bandwidth for Wideband Phased Array Application", Progress
In Electromagnetics Research, PIER, 2006.
[6] C. A. Balanis. "Antenna Theory, Analysis and Design", John Willey
and Sons INC, New York, 2005
[7] G. S. N. Raju. "Antenna And Wave Propagation", Pearson Education,
1st Ed., New Delhi, 2008