Bayesian Optimisation of a Frequency Selective Surface Using a Regularised Objective Function

Kilian Bihannic (1) , Jérémy Omer (1) , Renaud Loison (2) , Guillaume Reille (3)

1 IRMAR - Institut de Recherche Mathématique de Rennes
2 IETR - Institut d'Électronique et des Technologies du numéRique
3 Thales DMS France, SAS

This work introduces a penalty-based regularisation to optimise the geometric parameters of a periodic frequency selective surface. The equivalent circuit of a multi-layer bandpass filter is used to illustrate the benefits of the approach for wideband applications. The proposed regularisation is obtained by convolving the frequency response and the desired thresholds before measuring the infraction. We apply bayesian optimisation on the unconstrained optimisation problem and assess the performance of the strategy by the number of objective function evaluations. A faster convergence is observed with the proposed regularisation.

Mots clés: Electromagnetics; Frequency Selective Surface; Regularisation; Wideband Filtering; Bayesian Optimisation; Electromagnetics

Domaines: Statistiques [math.ST]; Electromagnétisme; Optimisation et contrôle [math.OC]

Kilian Bihannic, Jérémy Omer, Renaud Loison, Guillaume Reille. Bayesian Optimisation of a Frequency Selective Surface Using a Regularised Objective Function. 16th European Conference on Antennas and Propagation (EuCAP), Mar 2022, Madrid, Spain. ⟨10.23919/EuCAP53622.2022.9769068⟩. ⟨hal-03770686⟩