Abstract
Fast surrogate models are crucially important to reduce the cost of design process of antenna structures. Due to curse of dimensionality, standard (data-driven) modeling methods exhibit serious limitations concerning the number of independent geometry parameters that can be handled but also (and even more importantly) their parameter ranges. In this work, a design-oriented modeling framework is proposed in which the surrogate is constructed in the region of interest defined by a set of reference designs, optimized with respect to user-selected figures of interest (e.g., operating frequencies, substrate permittivity, etc.). The model domain is spanned by the simplexes obtained by triangulation of the reference designs, further extended into their orthogonal complements. Constraining the surrogate model domain this way allows for considerable reduction of the number of training data samples necessary to build the model, as compared to the traditional approach where the sampling is normally performed over a hypercube defined by the lower/upper bounds of the antenna parameters. Our considerations are illustrated using two examples: a UWB monopole, and a dual-band patch antenna.
Citations
-
0
CrossRef
-
0
Web of Science
-
0
Scopus
Authors (2)
Cite as
Full text
full text is not available in portal
Keywords
Details
- Category:
- Conference activity
- Type:
- publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)
- Title of issue:
- 12th European Conference on Antennas and Propagation (EuCAP 2018) strony 694 - 699
- Language:
- English
- Publication year:
- 2018
- Bibliographic description:
- Kozieł S., Sigurosson A.: Design-Oriented Constrained Modeling of Antenna Structures// 12th European Conference on Antennas and Propagation (EuCAP 2018)/ : , 2018, s.694-699
- DOI:
- Digital Object Identifier (open in new tab) 10.1049/cp.2018.1053
- Verified by:
- Gdańsk University of Technology
seen 118 times
Recommended for you
Accurate Modeling of Antenna Structures by Means of Domain Confinement and Pyramidal Deep Neural Networks
- S. Kozieł,
- N. Calik,
- P. Mahouti
- + 1 authors