Neural network simulation of a dielectric ring resonator antenna

✍ Scribed by Igor Ratner; Hassan Ali; Emil M. Petriu

• Book ID: 104426247
• Publisher: Elsevier Science
• Year: 1998
• Tongue: English
• Weight: 734 KB
• Volume: 44
• Category: Article
• ISSN: 1383-7621
• DOI: 10.1016/s1383-7621(97)00064-7

✦ Synopsis

This paper discusses the application ol'neural network (NN) techniques in the modelling dan electromagnetic (EM) field problem consisting of a dielectric-ring resonator antenna. The NN takes into consideration the geometrical and material parameters of the antenna. and the input rellection coefficient wlues for dilferent frequencies in the bandwidth ol'interest. The NN is trained o&line using results obtained with the finite element method (FEM). The NN is considered as a nonlinear function approximator and the L,evznberg~Mnry~lardt algorithm is used to solve the corresponding least-squares optimization problem. The NN approach is found to probide A tremendous comput:ltion;J speed improvement as well as computer memory reduction compared to the traditional numerical metlwds of' analysis.