Title: Artificial neural network design of stub microstrip band-pass filters

Authors: Geetam Singh Tomar; Vivek Singh Kushwah; Sarita Singh Bhadauria

Addresses: Department of Electrical and Computer Engineering, University of West Indies, St. Augustine Campus, Trinidad and Tobago; Machine Intelligence Research Lab, 223 New Jiwagi Nagar 474011, Gwalior, India; Department of Electronics, Amity School of Engineering and Technology, 474020, Gwalior, India; Department of Electronics, Madhav Institute of Technology and Science, 474005, Gwalior, India ' Department of Electrical and Computer Engineering, University of West Indies, St. Augustine Campus, Trinidad and Tobago; Machine Intelligence Research Lab, 223 New Jiwagi Nagar 474011, Gwalior, India; Department of Electronics, Amity School of Engineering and Technology, 474020, Gwalior, India; Department of Electronics, Madhav Institute of Technology and Science, 474005, Gwalior, India ' Department of Electrical and Computer Engineering, University of West Indies, St. Augustine Campus, Trinidad and Tobago; Machine Intelligence Research Lab, 223 New Jiwagi Nagar 474011, Gwalior, India; Department of Electronics, Amity School of Engineering and Technology, 474020, Gwalior, India; Department of Electronics, Madhav Institute of Technology and Science, 474005, Gwalior, India

Abstract: In this paper, an artificial neural network (ANN) design technique for a stub microstrip band-pass filter is presented. Essential dimensions of the microstrip filter layout are used to get the relationship of the input-outputs for ANN model. This paper presents the design and analysis of stub microstrip band-pass filter at mid-band frequency 1.8 GHz, which produced improved bandwidth and minimum insertion loss of -0.5899 dB and return loss of -36.67 dB. Artificial neural network architecture has been proposed to determine the magnitude variation of scattering parameters (S-parameters) of the microstrip band-pass filters for various dimensions. The ANN model produced has been exposed to be as exact and veracious as an EM simulator and it is computationally more effective in the design. The simulation is performed using the commercial software IE3D 14.1 and ANN training of S-parameters are performed in MATLAB 7.1.

Keywords: stub microstrip band pass filters; ANN modelling; MATLAB; IE3D EM simulation; sparameters; training algorithm; artificial neural networks; ANN design; electromagnetic simulation.

DOI: 10.1504/IJUWBCS.2014.060987

International Journal of Ultra Wideband Communications and Systems, 2014 Vol.3 No.1, pp.38 - 49

Received: 27 Feb 2013
Accepted: 12 Feb 2014

Published online: 23 May 2014 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article