Title :
Neural network-based characterization of microwave applicator loaded with multilayer dielectric
Author :
Zoran Stanković;Bratislav Milovanović;Nebojša Dončov;Aleksandar Marinčić
Author_Institution :
Electronic Engineering, Aleksandra Mevdvedeva 14, 18000 Nis, Serbia
Abstract :
In this paper, new neural network approach for characterization of cylindrical metallic cavity loaded with multilayer dielectric is suggested. Such cavity configuration has a great importance in realization of microwave resonant applicators, widely used for thermal processing of multilayer materials. Proposed neural model is based on representation of multilayer cavity load via several plan parallel homogeneous dielectric slabs and superposition of separate influence of each dielectric slab parameters on the cavity resonant frequency. Model is incorporated into MLP neural network enabling its efficient implementation on modest hardware platform. Suggested approach is verified on the example of circular cylindrical metallic cavity loaded with two-layer dielectric.
Keywords :
"Multi-layer neural network","Neural networks","Applicators","Electromagnetic heating","Resonant frequency","Slabs","Resonance","Dielectric materials","Nonhomogeneous media","Transmission line measurements"
Conference_Titel :
Telecommunication in Modern Satellite, Cable, and Broadcasting Services, 2009. TELSIKS ´09. 9th International Conference on
Print_ISBN :
978-1-4244-4382-6
DOI :
10.1109/TELSKS.2009.5339521