Enhanced uniform data sampling for constrained data‐driven modeling of antenna input characteristics
Abstract
Data-driven surrogates are the most popular replacement models utilized in many fields of engineering and science, including design of microwave and antenna structures. The primary practical issue is a curse of dimensionality which limits the number of independent parameters that can be accounted for in the modelling process. Recently, a performance-driven modelling technique has been proposed where the constrained domain of the model is spanned by a set of reference designs optimized with respect to selected figures of interest. This approach allows for significant improvement of prediction power of the surrogates without the necessity of reducing the parameter ranges. Yet, uniform allocation of the training data samples in the constrained domain remains a problem. Here, a novel design of experiments technique ensuring better sample uniformity is proposed. Our approach involves uniform sampling on the domain-spanning manifold and linear transformation of the remaining sample vector components onto orthogonal directions with respect to the manifold. Two antenna examples are provided to demonstrate the advantages of the technique, including application case studies (antenna optimization).
Citations
-
3
CrossRef
-
0
Web of Science
-
2
Scopus
Authors (4)
Cite as
Full text
- Publication version
- Accepted or Published Version
- License
- Copyright (2019 John Wiley & Sons, Ltd.)
Keywords
Details
- Category:
- Articles
- Type:
- artykuły w czasopismach
- Published in:
-
INTERNATIONAL JOURNAL OF NUMERICAL MODELLING-ELECTRONIC NETWORKS DEVICES AND FIELDS
no. 32,
pages 1 - 11,
ISSN: 0894-3370 - Language:
- English
- Publication year:
- 2019
- Bibliographic description:
- Kozieł S., Sigurdsson A., Pietrenko-Dąbrowska A., Szczepański S.: Enhanced uniform data sampling for constrained data‐driven modeling of antenna input characteristics// INTERNATIONAL JOURNAL OF NUMERICAL MODELLING-ELECTRONIC NETWORKS DEVICES AND FIELDS -Vol. 32,iss. 5 (2019), s.1-11
- DOI:
- Digital Object Identifier (open in new tab) 10.1002/jnm.2584
- Bibliography: test
-
- Nocedal J, Wright S. Numerical Optimization. 2nd ed. New York: Springer; 2006. open in new tab
- Fernandez Pantoja M, Rubio Bretones A, Gomez Martin R. Benchmark antenna problems for evolutionary optimization algorithms. IEEE Trans Antennas Propag. 2007;55(4):1111-1121. open in new tab
- Lalbakhsh A, Afzal MU, Esselle KP. Multiobjective particle swarm optimization to design a time-delay equalizer metasurface for an electromagnetic band-gap resonator antenna. IEEE Antennad Wirel Propag Lett. 2017;16:915-915. open in new tab
- Darvish A, Ebrahimzadeh A. Improved fruit-fly optimization algorithm and its applications in antenna array synthesis. IEEE Trans Antennas Propag. 2018;66(4):1756-1766. open in new tab
- Wang J, Yang XS, Wang BZ. Efficient gradient-based optimization of pixel antenna with large-scale connections. IET Microwaves Antennas Propag. 2018;12(3):385-389. open in new tab
- Ochoa JS, Cangellaris AC. Random-space dimensionality reduction for expedient yield estimation of passive microwave structures. IEEE Trans Microwave Theory Tech. 2013;61(12):4313-4321. open in new tab
- Kouassi A, Nguyen-Trong N, Kaufmann T, Lalléchère S, Bonnet P, Fumeaux C. Reliability-aware optimization of a wideband antenna. IEEE Trans Antennas Propag. 2016;64(2):450-460. open in new tab
- Abdel-Malek HL, Hassan ASO, Soliman EA, Dakroury SA. The ellipsoidal technique for design centering of microwave circuits exploiting space-mapping interpolating surrogates. IEEE Trans Microwave Theory Tech. 2006;54(10):3731-3738.
- Simpson TW, Pelplinski JD, Koch PN, Allen JK. Metamodels for computer-based engineering design: survey and recommendations. Eng Comput. 2001;17(2):129-150. open in new tab
- Bandler JW, Georgieva N, Ismail MA, Rayas-Sánchez JE, Zhang QJ. A generalized space mapping tableau approach to device modeling. IEEE Trans Microwave Theory Tech. 2001;49(1):67-79. open in new tab
- Baratta IA, de Andrade CB, de Assis RR, Silva EJ. Infinitesimal dipole model using space mapping optimization for antenna placement. IEEE Antennas Wirel Propag Lett. 2018;17(1):17-20. open in new tab
- Xu J, Li M, Chen R. Space mapping optimisation of 2D array elements arrangement to reduce the radar cross-scattering. IET Microwaves Antennas Propag. 2017;11(11):1578-1582. open in new tab
- Su Y, Lin J, Fan Z, Chen R. Shaping optimization of double reflector antenna based on manifold mapping, Int Applied Computational Electromagnetic Society Symp. (ACES), pp. 1-2, 2017.
- Chavez-Hurtado JL, Rayas-Sanchez JE. Polynomial-based surrogate modeling of RF and microwave circuits in frequency domain exploiting the multinomial theorem. IEEE Trans Microwave Theory Tech. 2016;64(12):4371-4381. open in new tab
- Couckuyt I. Forward and inverse surrogate modeling of computationally expensive problems, Ph.D. Thesis, Ghent University, 2013.
- Kabir H, Wang Y, Yu M, Zhang QJ. Neural network inverse modeling and applications to microwave filter design. IEEE Trans Microwave Theory Tech. 2008;56(4):867-879. open in new tab
- Jacobs JP, Koziel S. Reduced-cost microwave filter modeling using a two-stage Gaussian process regression approach. Int J RF Microwave Comput Aided Eng. 2014;25(5):453-462. open in new tab
- Zhang J, Zhang C, Feng F, Zhang W, Ma J, Zhang QJ. Polynomial chaos-based approach to yield-driven EM optimization. IEEE Trans Microwave Theory Tech. 2018;66(7):3186-3199. open in new tab
- Koziel S, Bekasiewicz A. Rapid dimension scaling of triple-band antennas by means of inverse surrogate modeling, IEEE Antennas Prop Symp, 2017. open in new tab
- Taskin G, Kaya H, Bruzzone L. Feature selection based on high dimensional model representation for hyperspectral images. IEEE Trans Image Process. 2017;26(6):2918-2928. open in new tab
- Ma S, Aybat NS. Efficient optimization algorithms for robust principal component analysis and its variants. Proc IEEE. 2018;106(8):1411-1426. open in new tab
- Koziel S, Bekasiewicz A. Computationally feasible narrow-band antenna modeling using response features. Int J RF Microwave Comput Aided Eng. 2017;27(4). open in new tab
- Echeverria D, Lahaye D, Encica L, Lomonova EA, Hemker PW, Vandenput AJA. Manifold-mapping optimization applied to linear actu- ator design. IEEE Trans Magn. 2006;42(4):1183-1186. open in new tab
- Koziel S, Bekasiewicz A. On reduced-cost design-oriented constrained surrogate modeling of antenna structures. IEEE Antennas Wirel Propag Lett. 2017;16:1618-1621. open in new tab
- Koziel S. Low-cost data-driven surrogate modeling of antenna structures by constrained sampling. IEEE Antennas Wirel Propag Lett. 2017;16:461-464. open in new tab
- Santner TJ, Williams BJ, Notz WI. Space-filling designs for computer experiments. In: The Design and Analysis of Computer Experiments. Springer Series in Statistics. New York: Springer; 2003:121-161. open in new tab
- Steponavice I, Shirazi-Manesh M, Hyndman RJ, Smith-Miles K, Villanova L. On sampling methods for costly multi-objective black-box optimization. In: Advances in Stochastic and Deterministic Global Optimization. New York: Springer; 2016:273-296. open in new tab
- Leary S, Bhaskar A, Keane A. Optimal orthogonal-array-based Latin hypercubes. J Appl Stat. 2003;30(5):585-598. open in new tab
- Giunta AA, Wojtkiewicz SF, Eldred MS. Overview of modern design of experiments methods for computational simulations, American Institute of Aeronautics and Astronautics, Paper AIAA 2003-0649, 2003. open in new tab
- Borouchaki H, George PL, Lo SH. Optimal Delaunay point insertion. Int J Numer Methods Eng. 1996;39(20):3407-3437. open in new tab
- Koziel S, Sigurdsson AT, Szczepanski S. Uniform sampling in constrained domains for low-cost surrogate modeling of antenna input characteristics. IEEE Antennas Wirel Propag Lett. 2018;17(1):164-167. open in new tab
- Chen Y-C, Chen S-Y, Hsu P. Dual-band slot dipole antenna fed by a coplanar waveguide, IEEE Int Symp Ant Prop., pp. 3589-3592, 2006.
- Koziel S, Bekasiewicz A, Leifsson L. Rapid EM-driven antenna dimension scaling through inverse modeling. IEEE Antennas Wirel Propag Lett. 2016;15:714-717. open in new tab
- Koziel S. Fast simulation-driven antenna design using response-feature surrogates. Int J RF Microwave Comput Aided Eng. 2015;25(5):394-402. open in new tab
- Verified by:
- Gdańsk University of Technology
seen 71 times