Recent Advances in Performance-Driven Surrogate Modeling of High-Frequency Structures - Publication - Bridge of Knowledge

Your account

login

Search

Recent Advances in Performance-Driven Surrogate Modeling of High-Frequency Structures

Abstract

Design of high‐frequency structures, including microwave and antenna components, heavily relies on full‐wave electromagnetic (EM) simulation models. Their reliability comes at a price of a considerable computational cost. This may lead to practical issues whenever numerous EM analyses are to be executed, e.g., in the case of parametric optimization. The difficulties entailed by massive simulations may be mitigated by the use of fast surrogates, among which data‐driven models are the most popular ones due to their versatility and accessibility. Unfortunately, conventional modeling techniques are significantly affected by the curse of dimensionality. It is particularly restrictive in the case of high‐frequency components, typically exhibiting highly nonlinear characteristics. Recently, the concept of performance‐driven modeling has been proposed where the surrogate model setup is focused on a small subset of the parameter space, containing the designs that are optimal or nearly optimal with respect to the considered performance figures. Domain confinement allows for a dramatic reduction of the number of training data samples needed for rendering reliable surrogates valid over wide ranges of the system parameters. In this paper, we review some of the recent techniques employing these concepts, discuss their properties, and illustrate them using real‐world examples of antenna and microwave components.

Citations

  • 1

    CrossRef

  • 0

    Web of Science

  • 1

    Scopus

Authors (2)

Cite as

Full text

download paper
downloaded 39 times
Publication version
Accepted or Published Version
License
Copyright (2020 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. 33,
ISSN: 0894-3370
Language:
English
Publication year:
2020
Bibliographic description:
Kozieł S., Pietrenko-Dąbrowska A.: Recent Advances in Performance-Driven Surrogate Modeling of High-Frequency Structures// INTERNATIONAL JOURNAL OF NUMERICAL MODELLING-ELECTRONIC NETWORKS DEVICES AND FIELDS -Vol. 33,iss. 6 (2020), s.e2706-
DOI:
Digital Object Identifier (open in new tab) 10.1002/jnm.2706
Bibliography: test
  1. Chaloun T, Ziegler V, Menzel W. Design of a dual-polarized stacked patch antenna for wide-angle scanning reflectarrays. IEEE Trans Antennas Propag. 2016;64(8):3380-3390. open in new tab
  2. Keerthi S, Hamad AH, Mian A, Clifford JJ, Majumdar PK, Chamok N, Ali M. Effect of heterogeneity in additively manufactured dielectric structures on RF response of microstrip patch antennas. Int J RF Microw Comput Aided Eng. 2018;28:e21234. open in new tab
  3. Wainwright G, Chen C. Low-profile broadband reflector antenna designed for low mutual coupling, European Conf Ant Propag (EuCAP). 2016. open in new tab
  4. Koziel S, Unnsteinsson SD. Expedited design closure of antennas by means of trust-region-based adaptive response scaling. IEEE Antennas Wirel Propag Lett. 2018;17(6):1099-1103. open in new tab
  5. Torun HM, Swaminathan, M. High-dimensional global optimization method for high-frequency electronic design. IEEE Trans Microwave Theory Tech. 2019;67(6):2128-2142. open in new tab
  6. Hosder S. Stochastic response surfaces based on non-intrusive polynomial chaos for uncertainty quantification. Int J Num Model Num Optim, 2012;3(1/2):117-139. open in new tab
  7. Ko J, Byun J, Park J, Kim H. Robust design of dual band/polarization patch antenna using sensitivity analysis and Taguchi's method. IEEE Trans Magn. 2011;47(5):1258-1261. open in new tab
  8. Booker AJ, Dennis JE, Frank PD, Serafini DB, Torczon V, Trosset MW. A rigorous framework for optimization of expensive functions by surrogates. Struct Optim. 1999;17:1-13. open in new tab
  9. Bandler JW, Cheng QS, Dakroury SA, Mohamed AS, Bakr MH, Madsen K, Søndergaard J. Space mapping: the state of the art. IEEE Trans Microwave Theory Tech. 2004;52(1):337-361. open in new tab
  10. Koziel S. Accurate low-cost microwave component models using shape- preserving response prediction. Int J Num Model: Electr Devices Fields. 2012;25(2):152-162. open in new tab
  11. Koziel S, Bekasiewicz A. Low-cost and reliable geometry scaling of compact microstrip couplers with respect to operating frequency, power split ratio, and dielectric substrate parameters. IET Microw Ant Propag. 2018;12(9):1508-1513. open in new tab
  12. Allaire G. A review of adjoint methods for sensitivity analysis, uncertainty quantification, and optimization in numerical codes. Ing de l'Automobile, SIA, 2015;836:33-36.
  13. Ghassemi M, Bakr M, Sangary N. Antenna design exploiting adjoint sensitivity- based geometry evolution. IET Microw Antennas Propag, 2013;7(4):268-276. open in new tab
  14. Sóbester A, Forrester AIJ, Toal DJJ, Tresidder E, Tucker S. Engineering design applications of surrogate-assisted optimization techniques. Optim Eng. 2012;15(1):243-265. open in new tab
  15. Koziel S, Bekasiewicz A. Reliable multistage optimization of antennas for multiple performance figures in highly dimensional parameter spaces. IEEE Ant Wireless Propag Lett. 2019;18(7):1522-1526.
  16. Bandler JW, Hailu DM, Madsen K, Pedersen F. A space-mapping interpolating surrogate algorithm for highly optimized EM-based design of microwave devices, IEEE Trans Microwave Theory Techn. 2004;52(11):2593-2600. open in new tab
  17. Ayed RB, Gong J, Brisset S, Gillon F, Brochet P. Three-level output space mapping strategy for electromagnetic design optimization. IEEE Trans Magn. 2012;48(2):671-674.
  18. Koziel S, Leifsson L. Simulation-driven design by knowledge-based response correction techniques. Cham: Springer; 2016. open in new tab
  19. Koziel S, Bandler JW, Madsen K. Space mapping with adaptive response correction for microwave design optimization. IEEE Trans Microwave Theory Tech. 2009;57:478-486. open in new tab
  20. Koziel S, Bekasiewicz A. Fast simulation-driven feature-based design optimization of compact dual-band microstrip branch-line coupler. Int J RF Microw Comput Aided Eng. 2015;26(1):13-20. open in new tab
  21. Rasmussen CE, Williams CKI. Gaussian processes for machine learning. Cambridge: MIT Press, 2006. open in new tab
  22. Jin Y. A comprehensive survey of fitness approximation in evolutionary computation. Soft Comput. 2005;9(1):3-12. open in new tab
  23. Gorissen D, Dhaene T, De Turck F. Evolutionary model type selection for global surrogate modeling. J Machine Learning Research. 2009;(10):2039-2078.
  24. Montegranario H, Espinosa J. Radial basis functions, In: Variational regularization of 3D Data, SpringerBriefs in Computer Science, New York: Springer, 2014. open in new tab
  25. Rayas-Sanchez JE. EM-based optimization of microwave circuits using artificial neural networks: the state-of-the-art. IEEE Trans Microwave Theory Tech. 2004;52(1):420-435. open in new tab
  26. Chávez-Hurtado JL, Rayas-Sánchez 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):4371-438. open in new tab
  27. Kitayama S, Arakawa M, Yamazaki K. Sequential approximate optimization using radial basis function network for engineering optimization. Optim Eng. 2011;12(4):535-557. open in new tab
  28. Kleijnen JPC. Kriging metamodeling in simulation: A review. European J Operat Research. 2009;192(3):707-716. open in new tab
  29. Angiulli G, Cacciola M, Versaci M. Microwave devices and antennas modelling by support vector regression machines. IEEE Trans Magn. 2007;43(4):1589- 1592. open in new tab
  30. Jacobs JP. Efficient resonant frequency modeling for dual-band microstrip antennas by gaussian process regression. IEEE Ant Wireless Propag Lett. 2015;14:337-341. open in new tab
  31. Du J, Roblin C. Statistical modeling of disturbed antennas based on the polynomial chaos expansion. IEEE Ant Wireless Prop Lett, 2017;16:1843-1846. open in new tab
  32. Schobi R, Sudret B, Wiart J. Polynomial-chaos-based kriging. Int J Uncertainty Quant, 2015;5(2):171-193. open in new tab
  33. Wu X, Peng X, Chen W, Zhang W. A developed surrogate-based optimization framework combining HDMR-based modeling technique and TLBO algorithm for high-dimensional engineering problems. Struct Multidisc Optim. 2019;60(2):663-680. open in new tab
  34. Liu H, Hervas JR, Ong YS, Cai J, Wang Y. An adaptive RBF-HDMR modeling approach under limited computational budget. Struct Multidisc Optim. 2018;57(3):1-18. open in new tab
  35. Koziel S, Bekasiewicz A. Computationally feasible narrow-band antenna modeling using response features. Int J RF Microw Comput Aided Eng. 2017;27(4):e21077. open in new tab
  36. Tropp JA, Gilbert AC. Signal recovery from random measurements via orthogonal matching pursuit. IEEE Trans Inf Theory. 2007;53(12):4655-4666. open in new tab
  37. Bakr MH, Bandler JW, Madsen K, Rayas-Sanchez JE, Sondergaard J. Space- mapping optimization of microwave circuits exploiting surrogate models. IEEE Trans Microwave Theory Tech. 2000;48(12):2297-2306. open in new tab
  38. Wang F, Cachecho P, Zhang W, Sun S, Li X, Kanj R, Gu C. Bayesian model fusion: large-scale performance modeling of analog and mixed-signal circuits by reusing early-stage data, IEEE Trans CAD Integr Circuits Systems. 2016;35(8):1255-1268. open in new tab
  39. Koziel S, Ogurtsov S, Couckuyt I, Dhaene T. Variable-fidelity electromagnetic simulations and co-kriging for accurate modeling of antennas. IEEE Trans Ant Propag. 2013;61(3):1301-1308. open in new tab
  40. Jacobs JP, Koziel S. Two-stage framework for efficient gaussian process modeling of antenna input characteristics. IEEE Trans Ant Propag. 2014;62(2):706-713. open in new tab
  41. Koziel S. Low-cost data-driven surrogate modeling of antenna structures by constrained sampling. IEEE Ant Wireless Prop Lett. 2017;16:461-464. open in new tab
  42. Koziel S, Bekasiewicz A. On reduced-cost design-oriented constrained surrogate modeling of antenna structures. IEEE Ant Wireless Prop Lett. 2017;16:1618- 1621. open in new tab
  43. Koziel S, Sigurðsson AT. Triangulation-based constrained surrogate modeling of antennas. IEEE Trans Ant Propag. 2018;66(8):4170-4179. open in new tab
  44. Koziel S, Sigurðsson AT, Szczepanski S. Uniform sampling in constrained domains for low-cost surrogate modeling of antenna input characteristics, IEEE Ant Wireless Prop Lett. 2018;17(1):164-167. open in new tab
  45. Koziel S, Pietrenko-Dabrowska A. Performance-based nested surrogate modeling of antenna input characteristics, IEEE Trans Ant Propag. 2019;67(5):2904-2912. open in new tab
  46. Koziel S, Pietrenko-Dabrowska A. Reduced-cost surrogate modelling of compact microwave components by two-level kriging interpolation. Eng Optim. 2019; open in new tab
  47. doi.org/10.1080/0305215X.2019.1630399. open in new tab
  48. Sim CYD, Chang MH, Chen BY. Microstrip-fed ring slot antenna design with wideband harmonic suppression. IEEE Trans Ant Propag. 2014;62(9):4828-4832. open in new tab
  49. Koziel S. Fast simulation-driven antenna design using response-feature surrogates. Int J RF Microw Comput Aided Eng. 2015;25(5):394-402. open in new tab
  50. Cheng SW, Dey T, Shewchuk J. Delaunay mesh generation, New York: Chapman and Hall; 2013. open in new tab
  51. Chen YC, Chen SY, Hsu P. Dual-band slot dipole antenna fed by a coplanar waveguide. IEEE Int Symp Ant Propag. 2006.
  52. Ai M, Kong X, Li K. A general theory for orthogonal array based latin hypercube sampling. Statistica Sinica. 2016;26(2):761-777. open in new tab
  53. Koziel S, Bekasiewicz A. Rapid simulation-driven multi-objective design optimization of decomposable compact microwave passives. IEEE Trans Microwave Theory Techn. 2016;64(8):2454-2461. open in new tab
Verified by:
Gdańsk University of Technology

seen 80 times

Recommended for you

Accurate Modeling of Antenna Structures by Means of Domain Confinement and Pyramidal Deep Neural Networks

2022

Two-Stage Variable-Fidelity Modeling of Antennas with Domain Confinement

2022

Design-Oriented Two-Stage Surrogate Modeling of Miniaturized Microstrip Circuits with Dimensionality Reduction

2020

Surrogate modeling of impedance matching transformers by means of variable‐fidelity electromagnetic simulations and nested cokriging

2020
Meta Tags