Bayesian optimization for solving high-frequency passive component design problems

• Autorzy: Baranowski Michal , Fotyga Grzegorz , Lamecki Adam , Mrozowski Michal

Identyfikatory

DOI

10.24425/bpasts.2022.141595

• Języki publikacji: EN

Abstrakty

EN

In this paper, the performance of the Bayesian Optimization (BO) technique applied to various problems of microwave engineering is studied. Bayesian optimization is a novel, non-deterministic, global optimization scheme that uses machine learning to solve complex optimization problems. However, each new optimization scheme needs to be evaluated to find its best application niche, as there is no universal technique that suits all problems. Here, BO was applied to different types of microwave and antenna engineering problems, including matching circuit design, multiband antenna and antenna array design, or microwave filter design. Since each of the presented problems has a different nature and characteristics such as different scales (i.e. number of design variables), we try to address the question about the generality of BO and identify the problem areas for which the technique is or is not recommended.

Słowa kluczowe

EN

high-frequency design; machine learning; Bayesian optimization

PL

optymalizacja bayesowska; konstrukcja o wysokiej częstotliwości; nauczanie maszynowe

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2022
• Tom: Vol. 70, nr 4
• Strony: art. no. e141595
• Opis fizyczny: Bibliogr. 37 poz., rys., tab.

Twórcy

autor

Baranowski Michal

• Gdańsk University of Technology, Gdańsk, Gabriela Narutowicza 11/12 80-233, Poland

• https://orcid.org/0000-0002-6109-0164

autor

Fotyga Grzegorz

• Gdańsk University of Technology, Gdańsk, Gabriela Narutowicza 11/12 80-233, Poland

• https://orcid.org/0000-0001-5268-6858

autor

Lamecki Adam

• Gdańsk University of Technology, Gdańsk, Gabriela Narutowicza 11/12 80-233, Poland
• EM Invent Sp. z o.o., Gdańsk, Trzy Lipy 3 80-172, Poland

• https://orcid.org/0000-0003-4747-7167

autor

Mrozowski Michal

• Gdańsk University of Technology, Gabriela Narutowicza 11/12, 80-233 Gdańsk, Poland

• https://orcid.org/0000-0002-1110-8717

Bibliografia

• [1] W. C. Gibson, The method of moments in electromagnetics. Chapman and Hall/CRC, 2007.
• [2] D.B. Davidson, Computational Electromagnetics for RF and Microwave Engineering, 2nd ed. Cambridge University Press, 2010, doi: 10.1017/CBO9780511778117.
• [3] G. Pelosi, R. Coccioli, and S. Selleri, “Quick finite elements for electromagnetic waves,” 1998.
• [4] P.E. Frandsen, K. Jonasson, H.B. Nielsen, and O. Tingleff, Unconstrained optimization. Technical University of Denmark, 1999.
• [5] N. Leszczynska, I. Couckuyt, T. Dhaene, and M. Mrozowski, “Low-cost surrogate models for microwave filters,” IEEE Microwave Wireless Compon. Lett., vol. 26, no. 12, pp. 969–971, 2016, doi: 10.1109/LMWC.2016.2623248.
• [6] B. Liu, H. Yang, and M.J. Lancaster, “Global optimization of microwave filters based on a surrogate model-assisted evolutionary algorithm,” IEEE Trans. Microwave Theory Tech., vol. 65, no. 6, pp. 1976–1985, 2017, doi: 10.1109/TMTT.2017.2661739.
• [7] S. Koziel, Q.S. Cheng, and J.W. Bandler, “Space mapping,” IEEE Microwave Mag., vol. 9, no. 6, pp. 105–122, 2008, doi: 10.1109/MMM.2008.929554.
• [8] J. Kennedy and R. Eberhart, “Particle swarm optimization,” in Proceedings of ICNN’95 – International Conference on Neural Networks, vol. 4, 1995, pp. 1942–1948, doi: 10.1109/ICNN.1995.488968.
• [9] M. Juneja and S.K. Nagar, “Particle swarm optimization algorithm and its parameters: A review,” in 2016 International Conference on Control, Computing, Communication and Materials (ICCCCM), 2016, pp. 1–5, doi: 10.1109/ICCCCM.2016.7918233.
• [10] J. Robinson and Y. Rahmat-Samii, “Particle swarm optimization in electromagnetics,” IEEE Trans. Antennas Propag., vol. 52, no. 2, pp. 397–407, 2004, doi: 10.1109/TAP.2004.823969.
• [11] D. Boeringer and D. Werner, “Particle swarm optimization versus genetic algorithms for phased array synthesis,” IEEE Trans. Antennas Propag., vol. 52, no. 3, pp. 771–779, 2004, doi: 10.1109/TAP.2004.825102.
• [12] N. Jin and Y. Rahmat-Samii, “Advances in particle swarm optimization for antenna designs: Real-number, binary, single-objective and multiobjective implementations,” IEEE Trans. Antennas Propag., vol. 55, no. 3, pp. 556–567, 2007, doi: 10.1109/TAP.2007.891552.
• [13] D. Cekus, P. Kwiatoń, M. Šofer, and P. Šofer, “Application of heuristic methods to identification of the parameters of discrete-continuous models,” Bull. Pol. Acad. Sci. Tech. Sci., vol. 70, no. 1, p. e140150, 2022, doi: 10.24425/bpasts.2022.140150.
• [14] M. Szczepanik and T. Burczyński, “Swarm optimization of stiffeners locations in 2-d structures,” Bull. Pol. Acad. Sci. Tech. Sci., vol. 60, no. 2, pp. 241–246, 2012, doi: 10.2478/v10175-012-0032-7.
• [15] B. Ufnalski, L. Grzesiak, and K. Gałkowski, “Particle swarm optimization of an iterative learning controller for the single-phase inverter with sinusoidal output voltage waveform,” Bull. Pol. Acad. Sci. Tech. Sci., vol. 61, no. 3, pp. 649–660, 2013, doi: 10.2478/bpasts-2013-0069.
• [16] J. Sykulski, “Computational electromagnetics for design optimisation: the state of the art and conjectures for the future,” Bull. Pol. Acad. Sci. Tech. Sci., vol. 57, no. 2, pp. 123–131, 2009, doi: 10.2478/v10175-010-0112-5.
• [17] C.E. Rasmussen and C.K.I. Williams, Gaussian processes for machine learning., ser. Adaptive computation and machine learning. MIT Press, 2006.
• [18] J. Zhou et al., “A trust-region parallel bayesian optimization method for simulation-driven antenna design,” IEEE Trans. Antennas Propag., 2020, doi: 10.1109/TAP.2020.3044393.
• [19] H.M. Torun and M. Swaminathan, “High-dimensional global optimization method for high-frequency electronic design,” IEEE Trans. Microwave Theory Tech., vol. 67, no. 6, pp. 2128–2142, 2019, doi: 10.1109/TMTT.2019.2915298.
• [20] P. Chen, B.M. Merrick, and T.J. Brazil, “Bayesian optimization for broadband high-efficiency power amplifier designs,” IEEE Trans. Microwave Theory Tech., vol. 63, no. 12, pp. 4263–4272, 2015, doi: 10.1109/TMTT.2015.2495360.
• [21] N. Knudde et al., “Data-efficient bayesian optimization with constraints for power amplifier design,” in 2018 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization (NEMO), 2018, pp. 1–3, doi: 10.1109/NEMO.2018.8503107.
• [22] A. Yang, W. Xue, C. Tian, J. Li, and L. Ye, “A design of silicon based horn antenna optimized using bayesian optimization,” in 2020 IEEE 6th International Conference on Computer and Communications (ICCC), 2020, pp. 438–442, doi: 10.1109/ICCC51575.2020.9345141.
• [23] K. Kandasamy et al., “Tuning hyperparameters without grad students: Scalable and robust bayesian optimisation with dragonfly,” J. Mach. Learn. Res., 2020.
• [24] J. Kim and S. Choi, “BayesO: A Bayesian optimization framework in Python,” 2017. [Online]. Available: https://bayeso.org.
• [25] P. Kozakowski and M. Mrozowski, “Automated cad of coupled resonator filters,” IEEE Microwave Wireless Compon. Lett., vol. 12, no. 12, pp. 470–472, 2002, doi: 10.1109/LMWC.2002.805932.
• [26] D. Marcano and F. Duran, Synthesis of Linear and Planar Arrays Using Genetic Algorithms. JohnWiley & Sons, Inc., 1999, ch. 6, pp. 157–180.
• [27] D.R. Jones, M. Schonlau, and W.J. Welch, “Efficient global optimization of expensive black-box functions,” J. Global Optim., vol. 13, p. 455–492, 1998, doi: 10.1023/A:1008306431147.
• [28] H.J. Kushner, “A New Method of Locating the Maximum Point of an Arbitrary Multipeak Curve in the Presence of Noise,” J. Basic Eng., vol. 86, no. 1, pp. 97–106, 03 1964.
• [29] P. Auer, “Using confidence bounds for exploitation-exploration trade-offs.” J. Mach. Learn. Res., vol. 3, pp. 397–422, 01 2002.
• [30] J. Zhang, Y. Li, Z. Liang, S. Zheng, and Y. Long, “Design of a multifrequency one-quarter-rings microstrip antenna,” IEEE Antennas Wirel. Propag. Lett., vol. 14, pp. 209–212, 2015, doi: 10.1109/LAWP.2014.2360412.
• [31] Y. Konishi and K. Uenakada, “The design of a bandpass filter with inductive strip – planar circuit mounted in waveguide,” IEEE Trans. Microwave Theory Tech., vol. 22, no. 10, pp. 869–873, 1974, doi: 10.1109/TMTT.1974.1128366.
• [32] J. Snoek, H. Larochelle, and R. Adams, “Practical bayesian optimization of machine learning algorithms,” Adv. Neural Inf. Process. Syst., vol. 4, 06 2012.
• [33] “Inventsim3D FEM electromagnetic field solver, ver. 2.0,” 2021. [Online]. Available: www.inventsim.com.
• [34] K.H. Mostapha, “CMA-ES inMATLAB,” 2015. [Online]. Available: https://yarpiz.com/235/ypea108-cma-es.
• [35] L. Balewski et al., “Step on it bringing fullwave finite-element microwave filter design up to speed,” IEEE Microwave Mag., vol. 21, no. 3, pp. 34–49, 2020, doi: 10.1109/MMM.2019.2958165.
• [36] J. Uher and J. Bornemann, Waveguide Components for Antenna Feed Systems: Theory and CAD. Artech House, 1993.
• [37] R.J. Cameron, C.M. Kudsia, and R.R. Mansour, Microwave Filters for Communication Systems. JohnWiley & Sons, Ltd, 2018, ch. 15, pp. 485–516, doi: 10.1002/9781119292371.ch15.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).