Gaussian-Process-Regression-Based Design of Ultrawide-Band and Dual-Band CPW-FED Slot Antennas

The applicability of Gaussian process (GP) regression as modeling tool within a genetic algorithm (GA) antenna optimization scheme is demonstrated. GP regression has recently been shown to be an efficient alternative to artificial neural networks (ANNs) when many accurate and fast estimates of antenna performance parameters, usually only obtainable from computationally intensive full-wave analyses, are required. GP regression has the important advantage that far fewer free parameters need to be determined; it furthermore is not subject to the implementation issues associated with neural nets. By using genetic algorithm optimization, two kinds of CPW-fed slot antennas were designed to operate within pre-specified frequency bands: an ultrawide-band (UWB) slot antenna with U-shaped tuning stub, and a dual-band slot loop antenna with separate T-shaped and insert tuning stubs. In both cases, the associated modeling problems were challenging, involving highly nonlinear mappings of several tunable geometry variables and frequency to S 11. This was especially so for the dual-band antenna, which had to operate in precisely positioned, comparatively narrow (compared to the UWB case) frequency bands (GSM and DECT) delineated by rapid changes in |S 11|. Despite using relatively few training data points given the dimensionality of the input spaces (a highly desirable model feature), the respective Gaussian process models were sufficiently accurate for the GA optimizer to yield antenna geometries that met the bandwidth specifications with ease, as was confirmed by comparison to moment-method-based simulations.

[1]  L. Xia,et al.  AN SUPPORT VECTOR REGRESSION BASED NONLINEAR MODELING METHOD FOR SIC MESFET , 2008 .

[2]  Carlos A. Brizuela,et al.  A Comparison of Genetic Algorithms, Particle Swarm Optimization and the Differential Evolution Method for the Design of Scannable Circular Antenna Arrays , 2009 .

[3]  Hao Ling,et al.  Application of Artificial Neural Networks to Broadband Antenna Design Based on a Parametric Frequency Model , 2007, IEEE Transactions on Antennas and Propagation.

[4]  J. P. Jacobs,et al.  GAUSSIAN PROCESS MODELING OF CPW-FED SLOT ANTENNAS , 2009 .

[5]  Ruimin Xu,et al.  Efficient Optimization of a Ka-Band Branch Waveguide Power Divider , 2008 .

[6]  D. Fu,et al.  GENETIC ALGORITHMS AND METHOD OF MOMENTS FOR THE DESIGN OF PIFAS , 2008 .

[7]  J.C. Lyke,et al.  Applications of neural networks in wireless communications , 2004, IEEE Antennas and Propagation Magazine.

[8]  Giuseppe Pelosi,et al.  GENETIC ALGORITHM OPTIMIZATION OF HIGH-EFFICIENCY WIDE-BAND MULTIMODAL SQUARE HORNS FOR DISCRETE LENSES , 2008 .

[9]  Carlos Camacho-Peñalosa,et al.  Dual-band, single CPW port, planar-slot antenna , 2003 .

[10]  S.H. Zainud-Deen,et al.  Direction of arrival and state of polarization estimation using Radial Basis Function Neural Network (RBFNN) , 2008, 2008 National Radio Science Conference.

[11]  Ozgur Ergul,et al.  Design and Simulation of Circular Arrays of Trapezoidal-Tooth Log-Periodic Antennas via Genetic Optimization , 2008 .

[12]  Qi-Zhong Liu,et al.  PATTERN SYNTHESIS OF CONFORMAL ANTENNA ARRAY BY THE HYBRID GENETIC ALGORITHM , 2008 .

[13]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[14]  Mustafa Turkmen,et al.  Neural Models for the Elliptic- and Circular-Shaped Microshield Lines , 2008 .

[15]  Chair,et al.  Ultrawide-band coplanar waveguide-fed rectangular slot antenna , 2004, IEEE Antennas and Wireless Propagation Letters.

[16]  Filiz Güneş,et al.  The Multi-Objective Optimization of Non-Uniform Linear Phased Arrays Using the Genetic Algorithm , 2009 .

[17]  Tao Yang,et al.  Mim Capacitor Modeling by Support Vector Regression , 2008 .

[18]  Thomas F. Coleman,et al.  Optimization Toolbox User's Guide , 1998 .