Deep-Learning-Based Inverse-Designed Millimeter-Wave Passives and Power Amplifiers

Emir Ali Karahan, Zheng Liu, Kaushik Sengupta

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

Abstract

This work describes deep-learning-enabled inverse design of multi-port electromagnetic (EM) structures co-designed with circuits that can enable the synthesis of novel high-frequency on-chip passives and circuits with designer scattering parameters in a rapid and automated fashion. The design of EM structures for high-frequency circuits typically starts from a pre-selected topology of unit functional elements that are subsequently optimized for the desired scattering parameters through time-consuming parameter sweeps, ad hoc optimization algorithms, or prior expert experience. In the space of all possible manufacturable EM structures, there is no reason to believe that these (and therefore, the co-designed circuits) will be close to being 'globally' optimal. Inverse design attempts to take a top-down approach to synthesis of EM structures and circuits by efficiently searching in a vastly larger design space of nearly arbitrary distributed structures for the desirable scattering parameters. To allow search of this design space, we need to eliminate time- and resource-intensive EM simulations in iterative search algorithms. To this end, we demonstrate a deep-learning-based forward model that captures accurately the scattering parameters of any arbitrary planar EM structure on chip and demonstration of rapid synthesis of millimeter-wave (mmWave) EM structures utilizing the aforementioned model. As a proof of concept, we synthesize a broadband, low-loss but seemingly arbitrary-looking 2-D output matching network for a 30-100-GHz mmWave power amplifier (PA). The PA achieves a power added efficiency (PAE) of 16%-24.7%, and a saturation power of 16.7-19.5 dBm across Psat,3,dB bandwidth of 30-94 GHz (103.2%). The PA supports both single-carrier and concurrent modulation at multi-gigabit per second. The design approaches can open up a new design space and allow rapid synthesis of complex RF-to-terahertz (THz) circuits and systems, reducing the need for prior experience, and time-intensive manual optimization typical for high-frequency circuits.

Original languageEnglish (US)
Pages (from-to)3074-3088
Number of pages15
JournalIEEE Journal of Solid-State Circuits
Volume58
Issue number11
DOIs
StatePublished - Nov 1 2023

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Keywords

  • 5G
  • 6G
  • CMOS
  • SiGe
  • broadband
  • deep learning
  • inverse design
  • millimeter wave (mmWave)
  • power amplifier (PA)
  • silicon
  • transmitter

Fingerprint

Dive into the research topics of 'Deep-Learning-Based Inverse-Designed Millimeter-Wave Passives and Power Amplifiers'. Together they form a unique fingerprint.

Cite this