CHARACTERIZATION OF LOSSY SIW RESONATORS BASED ON MULTILAYER PERCEPTRON NEURAL NETWORKS ON GRAPHICS PROCESSING UNIT

In recent years, Artiflcial Neural networks (ANNs) have been intensively employed to build smart model of microwave devices. In this paper a characterization of lossy SIW resonators by means of Multilayer Perceptron Neural Networks (MLPNNs) on Graphics Processing Unit (GPU), is presented. Once properly selected and trained, a MLPNN can evaluate the lossy SIW resonator's resonant frequency fr and the pertaining quality factor Q at a shorter time than the full-wave rigorous model. In this way, fast parametric models of SIW structures to employ for the design and optimization of microwave devices, exploiting the computational power of GPUs, can be obtained.

[1]  L. Boccia,et al.  Substrate integrated power combiners , 2012, 2012 6th European Conference on Antennas and Propagation (EUCAP).

[2]  Luigi Boccia,et al.  Compact Hybrid Coaxial Architecture for 3 GHz-10 GHz UWB Quasi-Optical Power Combiners , 2012 .

[3]  L. Boccia,et al.  Resonant Frequencies of Circular Substrate Integrated Resonators , 2008, IEEE Microwave and Wireless Components Letters.

[4]  Ming Luo,et al.  Prediction of the Electromagnetic Field in Metallic Enclosures Using Artificial Neural Networks , 2011 .

[5]  Jenq-Neng Hwang,et al.  Handbook of Neural Network Signal Processing , 2000, IEEE Transactions on Neural Networks.

[6]  Qi-Jun Zhang,et al.  Smart Modeling of Microwave Devices , 2010, IEEE Microwave Magazine.

[7]  L. Boccia,et al.  Computation of the Resonant Frequency and Quality Factor of Lossy Substrate Integrated Waveguide Resonators by Method of Moments , 2013 .

[8]  G Amendola,et al.  Method of Moments Analysis of Slotted Substrate Integrated Waveguide Arrays , 2011, IEEE Transactions on Antennas and Propagation.

[9]  G. Amendola,et al.  TWO DIMENSIONAL MULTI-PORT METHOD FOR ANALYSIS OF PROPAGATION CHARACTERISTICS OF SUBSTRATE INTEGRATED WAVEGUIDE , 2012 .

[10]  Pietro Laface,et al.  Parallel implementation of artificial neural network training , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[11]  Emilio Arnieri,et al.  Support Vector Regression Machines to Evaluate Resonant Frequency of Elliptic Substrate Integrate Waveguide Resonators , 2008 .

[12]  Jason Sanders,et al.  CUDA by example: an introduction to general purpose GPU programming , 2010 .

[13]  Wen-mei W. Hwu,et al.  GPU Computing Gems Jade Edition , 2011 .

[14]  L. Boccia,et al.  Annular ring slot radiating element for integrated millimeter wave arrays , 2012, 2012 6th European Conference on Antennas and Propagation (EUCAP).

[15]  G. Amendola,et al.  Fast Nonlinear Eigenvalues Analysis of Arbitrarily Shaped Substrate Integrated Waveguide (SIW) Resonators , 2009, IEEE Transactions on Magnetics.

[16]  Felipe Espinosa,et al.  Modeling Radiated Electromagnetic Emissions of Electric Motorcycles in Terms of Driving Profile Using Mlp Neural Networks , 2013 .

[17]  Luigi Boccia,et al.  ANALYSIS OF LOSSY SIW STRUCTURES BASED ON THE PARALLEL PLATES WAVEGUIDE GREEN'S FUNCTION , 2012 .

[18]  Giovanni Angiulli,et al.  Design of Square Substrate Integrated Waveguide Cavity Resonators: Compensation of Modelling Errors by Support Vector Regression Machines , 2012 .

[19]  Ray Walshe,et al.  Artificial Neural Network Simulation on CUDA , 2012, 2012 IEEE/ACM 16th International Symposium on Distributed Simulation and Real Time Applications.

[20]  G. Amendola,et al.  Analysis of Substrate Integrated Waveguide Structures Based on the Parallel-Plate Waveguide Green's Function , 2008, IEEE Transactions on Microwave Theory and Techniques.

[21]  Giovanni Angiulli,et al.  On the Computation of Nonlinear Eigenvalues in Electromagnetic Problems , 2007 .

[22]  S. He.  EVANESCENT-MODE SUBSTRATE INTEGRATED WA- VEGUIDE (SIW) FILTERS IMPLEMENTED WITH COM- PLEMENTARY SPLIT RING RESONATORS , 2011 .