An efficient algorithm for electromagnetic scattering by a set of perfect conducting cylindrical objects using the artificial neural network

In this article an efficient algorithm based on the wave concept iterative process is formulated and applied in order to investigate the electromagnetic scattering by a set of conducting arbitrarily shaped objects placed in the free space. In this approach, the cylindrical coordinates system is used as a modal base in order to develop the modal coefficients of the diffraction operator. This operator models the reaction of the environment expressing the electromagnetic coupling between each two pixels of the discretized surface. A study of electromagnetic coupling between two pixels positioned and oriented somehow in the free space is highlighted so as to determine the coupling operator for different positions and orientations of the emitted and received waves. Twelve coupling operators are developed. For a complex geometric shape structure, the determination of these characteristics involved the determination of interactions between each pixel and the others that constitute the discretized surface. This interaction involves the wave formulation already highlighted for each couple of pixels which implies a higher calculation time. In order to optimize the calculation time, the artificial neural networks are adopted with the feed‐forward architecture. The supervised learning has been chosen with the use of the resilient backpropagation algorithm.

[1]  H. Baudrand,et al.  The Wave Concept in Electromagnetism and Circuits: Theory and Applications , 2016 .

[2]  H. Baudrand,et al.  ANALYSIS OF MULTILAYERED CYLINDRICAL STRUCTURES USING A FULL WAVE METHOD , 2008 .

[3]  H. Baudrand,et al.  Near fields evaluated with the wave concept iterative procedure method for an E-polarisation plane wave scattered by cylindrical strips , 2003 .

[4]  Tomasz Pajchrowski,et al.  Neural Speed Controller Trained Online by Means of Modified RPROP Algorithm , 2015, IEEE Transactions on Industrial Informatics.

[5]  Ridha Bouallegue,et al.  Comparative study of learning-based localization algorithms for Wireless Sensor Networks: Support Vector regression, Neural Network and Naïve Bayes , 2015, 2015 International Wireless Communications and Mobile Computing Conference (IWCMC).

[6]  J. Volakis,et al.  Hybrid finite-element methodologies for antennas and scattering , 1997 .

[7]  Henri Baudrand,et al.  Wave concept iterative procedure applied to cylinders , 2004 .

[8]  H. Baudrand,et al.  Investigation of Electromagnetic Scattering by Arbitrarily Shaped Structures Using the Wave Concept Iterative Process , 2008 .

[9]  Paris A. Mastorocostas,et al.  Resilient back propagation learning algorithm for recurrent fuzzy neural networks , 2004 .

[10]  G. Panariello,et al.  Electromagnetic Scattering by Multiple Perfectly Conducting Arbitrary Polygonal Cylinders , 2008, IEEE Transactions on Antennas and Propagation.

[11]  S. M. Kirkup,et al.  Solution of Helmholtz Equation in the Exterior Domain by Elementary Boundary Integral Methods , 1995 .

[12]  H. Baudrand,et al.  A new full-wave hybrid differential-integral approach for the investigation of multilayer structures including nonuniformly doped diffusions , 2004, 2004 IEEE MTT-S International Microwave Symposium Digest (IEEE Cat. No.04CH37535).

[13]  P. Borderies,et al.  Integral Equations Physically-Based Preconditioner for Two-Dimensional Electromagnetic Scattering by Rough Surfaces , 2011, IEEE Transactions on Antennas and Propagation.

[14]  L. Landesa,et al.  The generalized forward-backward method for analyzing the scattering from targets on ocean-like rough surfaces , 1999, IEEE Antennas and Propagation Society International Symposium. 1999 Digest. Held in conjunction with: USNC/URSI National Radio Science Meeting (Cat. No.99CH37010).

[15]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[16]  Jeffrey A. Jargon,et al.  Applications of artificial neural networks to RF and microwave measurements , 2002 .

[17]  H. Baudrand,et al.  A new full-wave hybrid differential-integral approach for the investigation of multilayer structures including nonuniformly doped diffusions , 2005, IEEE Transactions on Microwave Theory and Techniques.

[18]  Qi-Jun Zhang,et al.  Neural Networks for RF and Microwave Design (Book + Neuromodeler Disk) , 2000 .

[19]  R. Harrington.  Boundary integral formulations for homogeneous material bodies , 1989 .

[20]  V. Jandhyala,et al.  Efficient solution of EFIE via low-rank compression of multilevel predetermined interactions , 2005, IEEE Transactions on Antennas and Propagation.

[21]  Rabindra K. Mishra,et al.  An overview of neural network methods in computational electromagnetics , 2002 .

[22]  H. Baudrand,et al.  WIP Study of Multiple Metallic Obstacle Scattering , 2013 .

[23]  Ali Gharsallah,et al.  Analysis of a microstrip antenna with fractal multilayer substrate using iterative method , 2001 .

[24]  Kuldip Gupta,et al.  Electromagnetic‐artificial neural network model for synthesis of physical dimensions for multilayer asymmetric coupled transmission structures (invited article) , 1999 .

[25]  H. Baudrand,et al.  Wave Concept Iterative Process Method for Electromagnetic or Photonic Jets: Numerical and Experimental Results , 2015, IEEE Transactions on Antennas and Propagation.

[26]  Martin A. Riedmiller,et al.  Advanced supervised learning in multi-layer perceptrons — From backpropagation to adaptive learning algorithms , 1994 .

[27]  Abdelhafid Khellaf,et al.  Modeling and design of printed antennas using neural networks , 2011 .