Data-driven model based design and analysis of antenna structures

Data-driven models, or metamodels, offer an efficient way to mimic the behaviour of computation-intensive simulators. Subsequently, the usage of such computationally cheap metamodels is indispensable in the design of contemporary antenna structures where computation-intensive simulations are often performed in a large scale. Although metamodels offer sufficient flexibility and speed, they often suffer from an exponential growth of required training samples as the dimensionality of the problem increases. In order to alleviate this issue, a Gaussian process based approach, known as Gradient-Enhanced Kriging (GEK), is proposed in this work to achieve cost-efficient modelling of antenna structures. The GEK approach incorporates adjoint-based sensitivity data in addition to function data obtained from electromagnetic simulations. The approach is illustrated using a dielectric resonator and an ultra-wideband antenna structures. The method demonstrates significant accuracy improvement with the less number of training samples over the Ordinary Kriging (OK) approach which utilises function data only. The discussed technique has been favourably compared with OK in terms of computational cost.

[1]  Ruimin Xu,et al.  Modeling of 3-D Vertical Interconnect Using Support Vector Machine Regression , 2006, IEEE Microwave and Wireless Components Letters.

[2]  Qi-Jun Zhang,et al.  High-Dimensional Neural-Network Technique and Applications to Microwave Filter Modeling , 2010, IEEE Transactions on Microwave Theory and Techniques.

[3]  Slawomir Koziel,et al.  Strategies for computationally feasible multi-objective simulation-driven design of compact RF/microwave components , 2016 .

[4]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[5]  Martin D. Buhmann,et al.  Radial Basis Functions: Theory and Implementations: Preface , 2003 .

[6]  Roger Woodard,et al.  Interpolation of Spatial Data: Some Theory for Kriging , 1999, Technometrics.

[7]  V. Gutierrez-Ayala,et al.  EM-Based Monte Carlo Analysis and Yield Prediction of Microwave Circuits Using Linear-Input Neural-Output Space Mapping , 2006, IEEE Transactions on Microwave Theory and Techniques.

[8]  S. Safavi-Naeini,et al.  ACCELERATED ANTENNA DESIGN METHODOLOGY EXPLOITING PARAMETERIZED CAUCHY MODELS , 2009 .

[9]  John W. Bandler,et al.  Fast EM Modeling Exploiting Shape-Preserving Response Prediction and Space Mapping , 2014, IEEE Transactions on Microwave Theory and Techniques.

[10]  T. Dhaene,et al.  Variable-Fidelity Electromagnetic Simulations and Co-Kriging for Accurate Modeling of Antennas , 2013, IEEE Transactions on Antennas and Propagation.

[11]  Tom Dhaene,et al.  Performance study of gradient-enhanced Kriging , 2015, Engineering with Computers.

[12]  Lei Xia,et al.  Support Vector Regression Model for Millimeter Wave Transitions , 2007 .

[13]  Qi-Jun Zhang,et al.  Neural Network Inverse Modeling and Applications to Microwave Filter Design , 2008, IEEE Transactions on Microwave Theory and Techniques.

[14]  Slawomir Koziel,et al.  Recent advances in space-mapping-based modeling of microwave devices , 2010 .

[15]  T. Simpson,et al.  Comparative studies of metamodelling techniques under multiple modelling criteria , 2001 .

[16]  Raafat R. Mansour,et al.  EM-based microwave circuit design using fuzzy logic techniques , 2006 .

[17]  T. Simpson,et al.  Comparative studies of metamodeling techniques under multiple modeling criteria , 2000 .

[18]  Timothy W. Simpson,et al.  Metamodels for Computer-based Engineering Design: Survey and recommendations , 2001, Engineering with Computers.

[19]  Piet Demeester,et al.  A Surrogate Modeling and Adaptive Sampling Toolbox for Computer Based Design , 2010, J. Mach. Learn. Res..

[20]  S. Koziel,et al.  A Space-Mapping Approach to Microwave Device Modeling Exploiting Fuzzy Systems , 2007, IEEE Transactions on Microwave Theory and Techniques.

[21]  Slawomir Koziel,et al.  Fast Multiobjective Optimization of Narrowband Antennas Using RSA Models and Design Space Reduction , 2015, IEEE Antennas and Wireless Propagation Letters.

[22]  Andy J. Keane,et al.  Recent advances in surrogate-based optimization , 2009 .

[23]  John W. Bandler,et al.  Rapid Yield Estimation and Optimization of Microwave Structures Exploiting Feature-Based Statistical Analysis , 2015, IEEE Transactions on Microwave Theory and Techniques.

[24]  Slawomir Koziel,et al.  Expedited EM-Driven Multiobjective Antenna Design in Highly Dimensional Parameter Spaces , 2014, IEEE Antennas and Wireless Propagation Letters.

[25]  Tom Dhaene,et al.  Efficient Multi-Objective Simulation-Driven Antenna Design Using Co-Kriging , 2014, IEEE Transactions on Antennas and Propagation.

[26]  Tom Dhaene,et al.  High dimensional Kriging metamodelling utilising gradient information , 2016 .

[27]  Gaofeng Wang,et al.  Dynamic Behavioral Modeling of Nonlinear Microwave Devices Using Real-Time Recurrent Neural Network , 2009, IEEE Transactions on Electron Devices.

[28]  G. Gary Wang,et al.  Review of Metamodeling Techniques in Support of Engineering Design Optimization , 2007, DAC 2006.

[29]  Tom Dhaene,et al.  Performance study of multi-fidelity gradient enhanced kriging , 2015 .

[30]  J.E. Rayas-Sanchez,et al.  EM-based optimization of microwave circuits using artificial neural networks: the state-of-the-art , 2003, IEEE Transactions on Microwave Theory and Techniques.

[31]  Qi-Jun Zhang,et al.  Statistical Neuro-Space Mapping Technique for Large-Signal Modeling of Nonlinear Devices , 2008, IEEE Transactions on Microwave Theory and Techniques.

[32]  Piet Demeester,et al.  ooDACE toolbox: a flexible object-oriented Kriging implementation , 2014, J. Mach. Learn. Res..

[33]  Christos Christodoulou,et al.  Support Vector Machines for Antenna Array Processing and Electromagnetics , 2006, Support Vector Machines for Antenna Array Processing and Electromagnetics.

[34]  Slawomir Koziel,et al.  Variable-fidelity optimization of antennas using adjoint sensitivities , 2014, 2014 Loughborough Antennas and Propagation Conference (LAPC).

[35]  Pierre Sagaut,et al.  Comparison of Gradient-Based and Gradient-Enhanced Response-Surface-Based Optimizers , 2010 .

[36]  Slawomir Koziel,et al.  Fast EM-Driven Size Reduction of Antenna Structures by Means of Adjoint Sensitivities and Trust Regions , 2015, IEEE Antennas and Wireless Propagation Letters.

[37]  Wei Hong,et al.  Behavioral Modeling of Power Amplifiers With Dynamic Fuzzy Neural Networks , 2010, IEEE Microwave and Wireless Components Letters.

[38]  S. Koziel,et al.  Two-Stage Framework for Efficient Gaussian Process Modeling of Antenna Input Characteristics , 2014, IEEE Transactions on Antennas and Propagation.

[39]  J. Alonso,et al.  Using gradients to construct cokriging approximation models for high-dimensional design optimization problems , 2002 .