bo liu

Automated Design of Microwave Antennas: An AI-empowered Approach

Antennas designated for present-day and future applications must fulfill stringent design specifications in terms of operational bandwidth, gain, radiation pattern, efficiency, and others. Conventional guidelines for antenna designs are often insufficient for the practical design of such contemporary antennas. This is mainly due to their complexity in terms of topological profiles, material composition, and electromagnetic characterization. Therefore, there is a present need for antenna designers to engage novel methodologies that allow for the efficient design exploration of modern antennas. This presentation provides an introduction to modern antenna design exploration methodology based on machine learning and heuristic optimization, making high-optimized antenna design solutions be obtained efficiently. The following topics will be included in the presentation: (1) a brief review of optimization methods for antenna design (2) surrogate model-assisted global optimization techniques (3) efficient antenna design exploration methods and case studies.

Bo LIU received the B.Eng. degree from Tsinghua University, China, in 2008 and the Ph.D. degree from University of Leuven (KU Leuven), Belgium, in 2012. Currently, he is a Professor of Electronic Design Automation at Universirty of Glasgow. He is a Fellow of IET and a Senior Member of IEEE. His research focuses on novel data-driven optimization and machine learning algorithms for electronic design and their real-world applications, including antenna, filter, analog and RF ICs. In terms of AI-driven antenna design, he is the inventor of the SADEA series. The SADEA series is the first to address the bottleneck of computationally expensive electromagnetic simulations together with poor or no initial design in antenna design exploration – this makes the AI-driven antenna design approach suitable for industrial requirements. More information can be found via https://www.gla.ac.uk/schools/engineering/staff/boliu/.