Title :
Modelling of the cylindrical metallic cavity loaded by lossy dielectric slab using neural networks
Author :
Milovanovic, Bratislav ; Stankovic, Zoran ; Ivkovic, Sladjana
Author_Institution :
Fac. of Electron. Eng., Nis Univ., Serbia
Abstract :
In this paper, the loaded cylindrical metallic cavity loaded by lossy dielectric slab is modelled using multilayer perceptron networks. A proper neural model is defined, which includes the dielectric slab losses and is used for modelling of the cavity with circular cross-section when lossy dielectric slab is placed at the bottom of the cavity. An original approach for significantly decreasing neural network training set is suggested. The results obtained show that the suggested approach provides microwave cavity modelling with high accuracy
Keywords :
cavity resonators; circuit tuning; dielectric losses; electrical engineering computing; learning (artificial intelligence); microwave devices; multilayer perceptrons; cylindrical metallic cavity; lossy dielectric slab; microwave cavity; mode tuning; modelling; multilayer perceptron; neural networks; training set; Applicators; Dielectric losses; Electromagnetic heating; Geometry; Load modeling; Neural networks; Resonance; Resonant frequency; Slabs; Transmission line matrix methods;
Conference_Titel :
Neural Network Applications in Electrical Engineering, 2000. NEUREL 2000. Proceedings of the 5th Seminar on
Conference_Location :
Belgrade
Print_ISBN :
0-7803-5512-1
DOI :
10.1109/NEUREL.2000.902402
