Performance Evaluation of ANN Models for the Analysis of Microstrip Low Pass Filters K.Sri Rama Krishna1, J.Lakshmi Narayana2 and L.Pratap Reddy3 (1) Professor of ECE and Dean R&D, Vignan’s Engineering College, Guntur, A.P. (2) Asst. Professor, ECE Department, Chalapathi Institute of Engineering & Technology, Guntur, A.P., India (3) Professor & Head of ECE, Jawaharlal Nehru Technological University, Hyderabad, A.P.Abstract: Filters play an important role in many RF/microwave applications and are used to select or confine the RF/microwave signals within assigned spectral limits. Emerging applications such as wireless communications continue to challenge RF/microwave filters with ever more stringent requirements like higher performance, smaller size, lighter weight, and lower cost. Microstrip filters are always preferred over the lumped filters at higher frequencies. In this paper we present the design and analysis of Microstrip Lowpass Filter using stepped-impedance and open circuited stubs at 1GHz. Also an artificial neural network model to determine the Magnitude and Phase variations of scattering parameters (S-parameters) of these filters is proposed for various frequencies. Performance of the proposed model is evaluated in terms of average and maximum estimated errors using different neural network training algorithms. Comparison of the results of the neural models with EM simulated results is also presented.
Keywords:
Microstrip Low Pass Filters, ANN models, S-parameters, Training
Algorithms
(
BibTex @ARTICLE{P1120841394, AUTHOR = {K.Sri Rama Krishna and J.Lakshmi Narayana and L.Pratap Reddy3}, TITLE = {Performance Evaluation of ANN Models for the Analysis of Microstrip Low Pass Filters},
JOURNAL = {ICGST International Journal on Artificial Intelligence and Machine Learning,
AIML},
YEAR = {2009}, VOLUME = {9}, ISSUE ={I}, PAGES = {9--18} } ( |
|||
|
P1120841394
