Machine-learning-based global optimization of microwave passives with variable-fidelity EM models and response features

• Published in: Scientific reports Vol. 14; no. 1; pp. 6250 - 20
• Main Authors: Koziel, Slawomir, Pietrenko-Dabrowska, Anna
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 15.03.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 639/166; 639/166/987; Algorithms; Benchmarks; Computer applications; EM-driven design; Globalized optimization; High-frequency engineering; Humanities and Social Sciences; Learning algorithms; Machine learning; multidisciplinary; Nature-inspired algorithms; Objective function; Science; Science (multidisciplinary); Surrogate-based design; Variable-fidelity models; Globalized optimization; Variable-fidelity models; Surrogate-based design; EM-driven design; Nature-inspired algorithms; Response features; High-frequency engineering
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-56823-7

Maximizing microwave passive component performance demands precise parameter tuning, particularly as modern circuits grow increasingly intricate. Yet, achieving this often requires a comprehensive approach due to their complex geometries and miniaturized structures. However, the computational burden of optimizing these components via full-wave electromagnetic (EM) simulations is substantial. EM analysis remains crucial for circuit reliability, but the expense of conducting rudimentary EM-driven global optimization by means of popular bio-inspired algorithms is impractical. Similarly, nonlinear system characteristics pose challenges for surrogate-assisted methods. This paper introduces an innovative technique leveraging variable-fidelity EM simulations and response feature technology within a kriging-based machine-learning framework for cost-effective global parameter tuning of microwave passives. The efficiency of this approach stems from performing most operations at the low-fidelity simulation level and regularizing the objective function landscape through the response feature method. The primary prediction tool is a co-kriging surrogate, while a particle swarm optimizer, guided by predicted objective function improvements, handles the search process. Rigorous validation demonstrates the proposed framework's competitive efficacy in design quality and computational cost, typically requiring only sixty high-fidelity EM analyses, juxtaposed with various state-of-the-art benchmark methods. These benchmarks encompass nature-inspired algorithms, gradient search, and machine learning techniques directly interacting with the circuit's frequency characteristics.