Near Field to Far Field Transformation Using Neural Networks and Source Reconstruction

Neural networks are proposed as an efficient tool able to perform near field to far field transformation, directly or through the application of the Theorem of Equivalence. A neural network can be trained to relate near field data with far field data or with an equivalent current distribution and then this one with the corresponding far field radiation pattern. Significant numerical examples are presented.

[1]  Michael Georgiopoulos,et al.  Performance of radial-basis function networks for direction of arrival estimation with antenna arrays , 1997 .

[2]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[3]  R. G. Ayestaran,et al.  Neural networks and equivalent source reconstruction for real antenna array synthesis , 2003 .

[4]  T. H. O'Donnell,et al.  Direction finding in phased arrays with a neural network beamformer , 1995 .

[5]  Michael Georgiopoulos,et al.  A neural network-based smart antenna for multiple source tracking , 2000 .

[6]  S. Costanzo,et al.  Far-Field Reconstruction from Phaseless Near-Field Data on a Cylindrical Helix , 2004 .

[7]  Päivi Koivisto,et al.  ON THE INFLUENCE OF INCOMPLETE RADIATION PATTERN DATA ON THE ACCURACY OF A SPHERICAL WAVE EXPANSION , 2005 .

[8]  Mats Gustafsson,et al.  Reconstruction of equivalent currents using a near-field data transformation - with radome applications , 2004 .

[9]  Michael Georgiopoulos,et al.  Applications of Neural Networks in Electromagnetics , 2001 .

[10]  Jean-Jacques Laurin,et al.  An implementation of a direction-finding antenna for mobile communications using a neural network , 1999 .

[11]  R. Harrington.  Time-Harmonic Electromagnetic Fields , 1961 .

[12]  Tapan K. Sarkar,et al.  A direct optimization approach for source reconstruction and NF-FF transformation using amplitude-only data , 2002 .

[13]  Alejandro Pazos,et al.  Avoiding interference in planar arrays through the use of artificial neural networks , 2002 .