Antenna Modeling Based on Two-Stage Gaussian Process Considering Sensitivity Information

For antenna modeling and optimization design, high-fidelity full-wave electromagnetic simulation software can generally be used to obtain training samples. However, this process takes a long time. To solve this problem, a two-stage Gaussian process (GP) considering electromagnetic sensitivity information is proposed. Based on the coarse grid and fine grid of electromagnetic simulation software, the first stage learns the mapping relationships of antenna performance and sensitivity of each parameter, simultaneously. In the second stage, the accurate surrogates are established based on the mapping relationships above obtained. Because the method in this study takes sensitivity information into consideration during the modeling process, it can better reflect the mapping relationship between antenna input and output, which can develop a more accurate surrogate model. The proposed two-stage GP surrogate model considering sensitivity information can significantly reduce the demand of high-fidelity training samples for modeling, and greatly save the simulation time of calling electromagnetic simulation software. Therefore, this method is more suitable for the problems of insufficient electromagnetic simulation samples. The proposed approach is evaluated by modeling and optimization of an inverted F antenna and an ultra-wideband planar monopole antenna. The results show that the method has high modeling accuracy with limited training samples given by high-fidelity electromagnetic simulation, which further verify its effectiveness and efficiency.

[1]  Bing-Zhong Wang,et al.  An Improved PSO Algorithm and Its Application to UWB Antenna Design , 2013, IEEE Antennas and Wireless Propagation Letters.

[2]  Xie Zheng,et al.  Antenna Optimization Design Based on Deep Gaussian Process Model , 2020, International Journal of Antennas and Propagation.

[3]  Lan Xu,et al.  Optimisation of reflection coefficient of microstrip antennas based on KBNN exploiting GPR model , 2018 .

[4]  Pooia Lalbakhsh,et al.  An Improved Model of Ant Colony Optimization Using a Novel Pheromone Update Strategy , 2013, IEICE Trans. Inf. Syst..

[5]  Qi-Jun Zhang,et al.  Parallel Gradient-Based EM Optimization for Microwave Components Using Adjoint- Sensitivity-Based Neuro-Transfer Function Surrogate , 2020, IEEE Transactions on Microwave Theory and Techniques.

[6]  Yubo Tian,et al.  Modeling of antenna resonant frequency based on co‐training of semi‐supervised Gaussian process with different kernel functions , 2021, International Journal of RF and Microwave Computer-Aided Engineering.

[7]  J. P. Jacobs,et al.  Efficient Resonant Frequency Modeling for Dual-Band Microstrip Antennas by Gaussian Process Regression , 2015, IEEE Antennas and Wireless Propagation Letters.

[8]  J.W. Bandler,et al.  Yield-Driven EM Optimization using Space Mapping-Based Neuromodels , 2001, 2001 31st European Microwave Conference.

[9]  Wei Shao,et al.  Multiparameter Modeling With ANN for Antenna Design , 2018, IEEE Transactions on Antennas and Propagation.

[10]  Taimoor Khan,et al.  Prediction of slot‐position and slot‐size of a microstrip antenna using support vector regression , 2018, International Journal of RF and Microwave Computer-Aided Engineering.

[11]  Yubo Tian,et al.  Differential Evolution Based Manifold Gaussian Process Machine Learning for Microwave Filter’s Parameter Extraction , 2020, IEEE Access.

[12]  Karu P. Esselle,et al.  Design of an artificial magnetic conductor surface using an evolutionary algorithm , 2017, 2017 International Conference on Electromagnetics in Advanced Applications (ICEAA).

[13]  Yong-xiu Xu,et al.  Optimal Design of Conical Horn Antenna Based on GP Model with Coarse Mesh , 2019, Iranian Journal of Science and Technology, Transactions of Electrical Engineering.

[14]  John W. Bandler,et al.  Fast space mapping modeling with adjoint sensitivity , 2011, 2011 IEEE MTT-S International Microwave Symposium.

[15]  John W. Bandler,et al.  Computer-aided design of RF and microwave circuits and systems , 2002 .

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

[17]  Qi-Jun Zhang,et al.  Parametric Modeling of Microwave Passive Components Using Sensitivity-Analysis-Based Adjoint Neural-Network Technique , 2013, IEEE Transactions on Microwave Theory and Techniques.

[18]  Fei‐yan Sun,et al.  DOA estimation based on support vector machine ensemble , 2019, International Journal of Numerical Modelling: Electronic Networks, Devices and Fields.

[19]  Saida Ibnyaich,et al.  The study of the ground plane effect on a Multiband PIFA Antenna by using Genetic Algorithm and Particle Swarm Optimization , 2016 .

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

[21]  Jing Gao,et al.  Resonant Frequency Modeling of Microwave Antennas Using Gaussian Process Based on Semisupervised Learning , 2020, Complex..

[22]  Kun-Chou Lee.  Application of Neural Network and Its Extension of Derivative to Scattering From a Nonlinearly Loaded Antenna , 2007, IEEE Transactions on Antennas and Propagation.

[23]  Yi Chen,et al.  Modeling and optimization of microwave filter by ADS‐based KBNN , 2017 .

[24]  Slawomir Koziel,et al.  Expedited Yield Optimization of Narrow- and Multi-Band Antennas Using Performance-Driven Surrogates , 2020, IEEE Access.

[25]  Robert B. Gramacy,et al.  Ja n 20 08 Bayesian Treed Gaussian Process Models with an Application to Computer Modeling , 2009 .

[26]  Francesco Grimaccia,et al.  Optimization of a Dual Ring Antenna by Means of Artificial Neural Network , 2014 .

[27]  M. A. Honarvar,et al.  Gain Enhancement of Wideband Circularly Polarized UWB Antenna Using FSS , 2020, Radio Science.

[28]  Slawomir Koziel,et al.  Multilevel microwave design optimization with automated model fidelity adjustment , 2014 .

[29]  Jing Jin,et al.  A Novel Training Approach for Parametric Modeling of Microwave Passive Components Using Padé via Lanczos and EM Sensitivities , 2020, IEEE Transactions on Microwave Theory and Techniques.

[30]  Shweta Rani,et al.  On the design and optimisation of new fractal antenna using PSO , 2013 .

[31]  Lei Chang,et al.  A Hybrid Method Based on Differential Evolution and Continuous Ant Colony Optimization and its Application on Wideband Antenna Design , 2012 .

[32]  Tian Yubo,et al.  Modeling the resonant frequency of compact microstrip antenna by the PSO‐based SVM with the hybrid kernel function , 2016 .

[33]  Yubo Tian,et al.  Antenna Optimization Based on Co-Training Algorithm of Gaussian Process and Support Vector Machine , 2020, IEEE Access.

[34]  K. Esselle,et al.  Simulation-driven particle swarm optimization of spatial phase shifters , 2016, 2016 International Conference on Electromagnetics in Advanced Applications (ICEAA).

[35]  Feng Feng,et al.  Parametric Modeling of Microwave Components Using Adjoint Neural Networks and Pole-Residue Transfer Functions With EM Sensitivity Analysis , 2017, IEEE Transactions on Microwave Theory and Techniques.

[36]  Bo Tian,et al.  Boresight gain optimization of an UWB monopole antenna using FDTD and genetic algorithm , 2010, 2010 IEEE International Conference on Ultra-Wideband.

[37]  Ruan Fangming.  Design and optimization of UWB antenna based on genetic algorithm , 2011 .

[38]  Ronghong Jin,et al.  Optimal design of ultra wideband antennas using a mixed model of 2‐D genetic algorithm and finite‐difference time‐domain , 2007 .