Advanced search
2 files | 603.70 KB Add to list

Cost-efficient modeling of antenna structures using Gradient Enhanced Kriging

Author
Organization
Abstract
Reliable yet fast surrogate models are indispensable in the design of contemporary antenna structures. Data-driven models, e.g., based on Gaussian Processes or support-vector regression, offer sufficient flexibility and speed, however, their setup cost is large and grows very quickly with the dimensionality of the design space. In this paper, we propose cost-efficient modeling of antenna structures using Gradient-Enhanced Kriging. In our approach, the training data set contains, apart from the EM-simulation responses of the structure at hand, also derivative data at the respective training locations obtained at little extra cost using adjoint sensitivity techniques. We demonstrate that introduction of the derivative information into the model allows for considerable reduction of the model setup cost (in terms of the number of training points required) without compromising its predictive power. The Gradient-Enhanced Kriging technique is illustrated using a dielectric resonator antenna structure. Comparison with conventional Kriging interpolation is also provided.
Keywords
SUPPORT VECTOR REGRESSION, IBCN, SPACE-MAPPING APPROACH, NEURAL-NETWORKS, DESIGN, OPTIMIZATION, TOOLBOX, Antenna modeling, electromagnetic simulation, surrogate modeling, Kriging, Gradient-Enhanced Kriging, computer-aided design

Downloads

  • 6547 i.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 316.18 KB
  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 287.52 KB

Citation

Please use this url to cite or link to this publication:

MLA
Ulaganathan, Selvakumar et al. “Cost-efficient Modeling of Antenna Structures Using Gradient Enhanced Kriging.” 2015 LOUGHBOROUGH ANTENNAS & PROPAGATION CONFERENCE (LAPC). 2015. 1–5. Print.
APA
Ulaganathan, S., Koziel, S., Bekasiewicz, A., Couckuyt, I., Laermans, E., & Dhaene, T. (2015). Cost-efficient modeling of antenna structures using Gradient Enhanced Kriging. 2015 LOUGHBOROUGH ANTENNAS & PROPAGATION CONFERENCE (LAPC) (pp. 1–5). Presented at the Loughborough Antennas & Propagation Conference (LAPC).
Chicago author-date
Ulaganathan, Selvakumar, S Koziel, A Bekasiewicz, Ivo Couckuyt, Eric Laermans, and Tom Dhaene. 2015. “Cost-efficient Modeling of Antenna Structures Using Gradient Enhanced Kriging.” In 2015 LOUGHBOROUGH ANTENNAS & PROPAGATION CONFERENCE (LAPC), 1–5.
Chicago author-date (all authors)
Ulaganathan, Selvakumar, S Koziel, A Bekasiewicz, Ivo Couckuyt, Eric Laermans, and Tom Dhaene. 2015. “Cost-efficient Modeling of Antenna Structures Using Gradient Enhanced Kriging.” In 2015 LOUGHBOROUGH ANTENNAS & PROPAGATION CONFERENCE (LAPC), 1–5.
Vancouver
1.
Ulaganathan S, Koziel S, Bekasiewicz A, Couckuyt I, Laermans E, Dhaene T. Cost-efficient modeling of antenna structures using Gradient Enhanced Kriging. 2015 LOUGHBOROUGH ANTENNAS & PROPAGATION CONFERENCE (LAPC). 2015. p. 1–5.
IEEE
[1]
S. Ulaganathan, S. Koziel, A. Bekasiewicz, I. Couckuyt, E. Laermans, and T. Dhaene, “Cost-efficient modeling of antenna structures using Gradient Enhanced Kriging,” in 2015 LOUGHBOROUGH ANTENNAS & PROPAGATION CONFERENCE (LAPC), Loughborough, United Kingdom, 2015, pp. 1–5.
@inproceedings{7237370,
  abstract     = {Reliable yet fast surrogate models are indispensable in the design of contemporary antenna structures. Data-driven models, e.g., based on Gaussian Processes or support-vector regression, offer sufficient flexibility and speed, however, their setup cost is large and grows very quickly with the dimensionality of the design space. In this paper, we propose cost-efficient modeling of antenna structures using Gradient-Enhanced Kriging. In our approach, the training data set contains, apart from the EM-simulation responses of the structure at hand, also derivative data at the respective training locations obtained at little extra cost using adjoint sensitivity techniques. We demonstrate that introduction of the derivative information into the model allows for considerable reduction of the model setup cost (in terms of the number of training points required) without compromising its predictive power. The Gradient-Enhanced Kriging technique is illustrated using a dielectric resonator antenna structure. Comparison with conventional Kriging interpolation is also provided.},
  author       = {Ulaganathan, Selvakumar and Koziel, S and Bekasiewicz, A and Couckuyt, Ivo and Laermans, Eric and Dhaene, Tom},
  booktitle    = {2015 LOUGHBOROUGH ANTENNAS & PROPAGATION CONFERENCE (LAPC)},
  isbn         = {978-1-4799-8943-0},
  keywords     = {SUPPORT VECTOR REGRESSION,IBCN,SPACE-MAPPING APPROACH,NEURAL-NETWORKS,DESIGN,OPTIMIZATION,TOOLBOX,Antenna modeling,electromagnetic simulation,surrogate modeling,Kriging,Gradient-Enhanced Kriging,computer-aided design},
  language     = {eng},
  location     = {Loughborough, United Kingdom},
  pages        = {1--5},
  title        = {Cost-efficient modeling of antenna structures using Gradient Enhanced Kriging},
  year         = {2015},
}

Web of Science
Times cited: