Loaded cylindrical metallic cavities modeling using neural networks

被引：0

作者：

Milovanovic, B ^{[1
]}

Stankovic, Z ^{[1
]}

Ivkovic, S ^{[1
]}

机构：

[1] Univ Nish, Fac Elect Engn, YU-18000 Nish, Yugoslavia

来源：

TELSIKS '99: 4TH INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS IN MODERN SATELLITE, CABLE AND BROADCASTING SERVICES, PROCEEDINGS, VOLS 1 AND 2 | 1999年

关键词：

microwave cavity; neural networks; modeling;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The feasibility of using neural networks for resonant frequencies determination in loaded cylindrical metallic cavities is presented in this paper. The load in the form of homogeneous dielectric slab with losses, which is located on the bot tom of the cavity, is considered. Using of classical multi-layer perception (MLP) network is illustrated through the example of TM113 modes determination in microwave cavity with circular cross-section. An original approach for decreasing neural network training set is used.

引用

页码：214 / 217

页数：4

共 9 条

[1]

DONCOV N, 1998, YUG MTT MICR REV, V5, P6

[2]

Haykin S., 1994, NEURAL NETWORKS COMP, V5, P363, DOI [10.1142/S0129065794000372, DOI 10.1142/S0129065794000372]

[3]

Hertz J., 1991, Introduction to the Theory of Neural Computation

[4]

IVKOVIC S, 1998, ETRAN98 C P, P337

[5]

IVKOVIC S, 1997, IEEE MTT TELSIKS97 C, P306

[6]

Milovanovic B, 1998, J MICROWAVE POWER EE, V33, P49

[7]

MILOVANOVIC B, 1997, TLM WORKSH MOD THEOR, P228

[8]

MLADENOVIC M, 1989, J MICROWAVE POWER EE, V24, P165

[9]

STANKOVIC Z, 1999, YUINFO99 KOPAONIK

← 1 →