Low-cost quasi-global optimization of expensive electromagnetic simulation models by inverse surrogates and response features

Abstract

Conceptual design of contemporary high-frequency structures is typically followed by a careful tuning of their parameters, predominantly the geometry ones. The process aims at improving the relevant performance figures, and may be quite expensive. The reason is that conventional design methods, e.g., based on analytical or equivalent network models, often only yield rough initial designs. This is especially the case for miniaturized components featuring considerable electromagnetic (EM) cross couplings, or antenna systems with non-negligible radiator coupling (e.g., MIMO, closely-spaced arrays). For reliability reasons, parametric optimization is carried out using EM simulation tools, which is a time-consuming task. In many cases, designer needs to resort to a global search, especially when handling several objectives and constraints is necessary, or the high-frequency structure under design is overly complex. Combination of both aforementioned factors makes it no longer possible to rely on engineering insight, even to detect a promising region of the design space. Unfortunately, nature-inspired algorithms, commonly employed for solving these tasks typically exhibit significant computational expenditures. This paper proposes a simple yet efficient method for globalized search using a response feature approach and inverse regression surrogates. Owing to less nonlinear dependence of the feature point coordinates on the system variables (as compared to the original responses, e.g., S-parameter frequency characteristics), our methodology permits a rapid identification of the most appropriate regions of the parametric space, and further design tuning by means of local routines. At the same time, the overall optimization cost is comparable to the cost of local procedures. The proposed approach is validated using several high-frequency structures (a dual-band antenna, a microstrip coupler, an impedance matching transformer) optimized under different design scenarios. Global search capability and computational efficiency are demonstrated through comprehensive comparisons with multiple-start local search, as well as particle swarm optimizer, a representative nature-inspired algorithm.

A machine learning-based comparative analysis of surrogate models for design optimisation in computational fluid dynamics

“…Surrogate modelling techniques [ [29] , [30] , [31] , [32] , [33] ] have gained popularity in optimising engineering design problems, with researchers focusing on different applications. Koziel and Pietrenko-Dabrowska [ 34 , 35 ] contribute to this field by addressing the challenges of designing and optimising high-frequency systems, especially antennas and microwave circuits.…”

A High-Quality Data Acquisition Method for Machine-Learning-Based Design and Analysis of Electromagnetic Structures

“…However, most data acquisition methods [29]- [33] are not suitable for EM-related ML applications. There have been many great works [34]- [42] that attempted to identify the most promising region of the parameter space and further tune the design by means of local routines. They improved the global optimization of expensive EM simulation models significantly.…”