A Design Methodology of MMIC Power Amplifiers Using AI-driven Design Techniques

Liyuan Xue*, Haijun Fan, Yuan Ding, Bo Liu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

285 Downloads (Pure)

Abstract

Designing a monolithic microwave integrated circuit (MMIC) power amplifier (PA) is challenging due to the involvement of multiple stages with tens of parameters and several types of simulations. To address this challenge, artificial intelligence (AI) techniques have gained significant attention. This paper presents an AI-driven design methodology for MMIC PAs, which incorporates a surrogate model-assisted global optimization algorithm, data-flow interface, and simulators. The proposed methodology is verified on a practical 3-stage PA design case that operates in 27–31 GHz and contains 30 variables. Notably, The case is successfully synthesized without an initial solution and exhibits good in-band performance consistency. The obtained results demonstrate the potential of AI-driven PA design for future applications.
Original languageEnglish
Title of host publication19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design (SMACD)
PublisherIEEE
ISBN (Electronic)9798350332650
DOIs
Publication statusPublished - 31 Jul 2023
Event19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design 2023 - Madeira Island, Portugal
Duration: 3 Jul 20235 Jul 2023
https://smacd-conference.org/

Conference

Conference19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design 2023
Abbreviated titleSMACD 2023
Country/TerritoryPortugal
Period3/07/235/07/23
Internet address

Keywords

  • artificial intelligence
  • global optimization
  • millimeter-wave
  • power amplifier

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering
  • Modelling and Simulation
  • Instrumentation

Fingerprint

Dive into the research topics of 'A Design Methodology of MMIC Power Amplifiers Using AI-driven Design Techniques'. Together they form a unique fingerprint.

Cite this