Related papers: Inverse Design of Compact and Wideband Inverted Doherty Power Amplifiers Using Deep Learning

Inverse Design of Compact and Wideband Inverted Doherty Power Amplifiers Using Deep Learning

URL: http://arxiv.org/abs/2606.27002v1
Date: Thu, 25 Jun 2026 13:19:38 GMT
Title: Inverse Design of Compact and Wideband Inverted Doherty Power Amplifiers Using Deep Learning
Abstract summary: This paper presents a deep learning-assisted methodology for the inverse synthesis of a compact, wideband inverted Doherty power amplifier (PA)<n>CNNs and genetic algorithms are jointly employed to generate pixelated Doherty combiner networks.<n>As a proof of concept, we design and fabricate a GaN HEMT Doherty PA with a pixelated output combiner.
Score: 9.885945418536052
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: This paper presents a deep learning-assisted methodology for the inverse synthesis of a compact, wideband inverted Doherty power amplifier (PA). Convolutional neural networks (CNNs) and genetic algorithms (GAs) are jointly employed to generate pixelated Doherty combiner networks that integrate load modulation, impedance matching, power combining, and phase compensation into a single structure. As a proof of concept, we design and fabricate a GaN HEMT Doherty PA with a pixelated output combiner. The prototype achieves a measured peak drain efficiency of 51%-63% and a 6-dB back-off efficiency of 48%-54% over 1.9-2.5 GHz. Within the same frequency range, the measured output power is 44+/-0.3 dBm. Furthermore, with digital predistortion (DPD) applied, the prototype circuit demonstrates an adjacent channel leakage ratio (ACLR) better than -53.2 dBc.

Related papers

DiffusionGemma Technical Report [72.10570774996219]
We introduce DiffusionGemma, a language model that uses discrete diffusion to generate text at exceptionally high speed.<n>Rather than decoding one token at a time, DiffusionGemma iteratively refines blocks of 256 tokens in parallel.<n>Our compute-efficient two-stage training pipeline uses fewer than 10% of the starting AR model's total training token budget.
arXiv Detail & Related papers (2026-07-31T16:11:46Z)
Deep Learning-Driven Inverse Design of Doherty Power Amplifiers Using Pixelated Combiners and Dual-State Impedance Synthesis [9.885945418536052]
We propose a three-port Doherty combiner design methodology that combines deep convolutional neural networks (CNNs), pixelated layout representations, and genetic algorithms (GA)<n>As a proof of concept, two GaN HEMT Doherty PA prototypes incorporating three-port pixelated combiners are designed and fabricated.
arXiv Detail & Related papers (2026-06-16T18:38:15Z)
Deep Learning-Driven Black-Box Doherty Power Amplifier with Pixelated Output Combiner and Extended Efficiency Range [10.090846922590462]
This article presents a deep learning-driven inverse design methodology for Doherty power amplifiers (PA) with multi-port pixelated output combiner networks.<n>A deep convolutional neural network (CNN) is developed and trained as an electromagnetic (EM) surrogate model.<n>We synthesize complex Doherty combiners that enable an extended back-off efficiency range using fully symmetrical devices.
arXiv Detail & Related papers (2026-03-17T14:23:58Z)
OpenDPDv2: A Unified Learning and Optimization Framework for Neural Network Digital Predistortion [10.484441707788127]
This paper presents OpenDPDv2, a unified framework for PA modeling, DPD learning, and model optimization.<n> optimization techniques feature a novel DPD algorithm, TRes-DeltaGRU, alongside two energy-efficient methods.
arXiv Detail & Related papers (2025-07-09T13:54:47Z)
Function Approximation for Reinforcement Learning Controller for Energy from Spread Waves [69.9104427437916]
Multi-generator Wave Energy Converters (WEC) must handle multiple simultaneous waves coming from different directions called spread waves. These complex devices need controllers with multiple objectives of energy capture efficiency, reduction of structural stress to limit maintenance, and proactive protection against high waves. In this paper, we explore different function approximations for the policy and critic networks in modeling the sequential nature of the system dynamics.
arXiv Detail & Related papers (2024-04-17T02:04:10Z)
Broadband parametric amplification in DARTWARS [64.98268713737]
Traveling-Wave Parametric Amplifiers (TWPAs) may be especially suitable for practical applications due to their multi-Gigahertz amplification bandwidth. The DARTWARS project aims to develop a KITWPA capable of achieving $20,$ dB of amplification. The measurements revealed an average amplification of approximately $9,$dB across a $2,$GHz bandwidth for a KITWPA spanning $17,$mm in length.
arXiv Detail & Related papers (2024-02-19T10:57:37Z)
Peripheral circuits for ideal performance of a travelling-wave parametric amplifier [0.0]
We investigate the required peripheral circuits to enable ideal performance for a high-gain travelling-wave parametric amplifier (TWPA) based on three-wave mixing (3WM) By embedding the TWPA in a network of superconducting diplexers, hybrid couplers and impedance matching networks, the amplifier can deliver a high stable gain with near-quantum-limited noise performance, with suppressed gain ripples. We demonstrate how the WIF-TWPAs can be used to construct controllable isolators with over 40 dB isolation over the full 4-8 GHz band.
arXiv Detail & Related papers (2023-10-18T11:57:15Z)
Josephson parametric amplifier with Chebyshev gain profile and high saturation [0.0]
We demonstrate a Josephson parametric amplifier design with a band-pass impedance matching network based on a third-order Chebyshev prototype. We measure eight amplifiers operating at 4.6 GHz that exhibit gains of 20 dB with less than 1 dB gain ripple and up to 500 MHz bandwidth. We characterize the system readout efficiency and its signal-to-noise ratio near saturation using a Sycamore processor.
arXiv Detail & Related papers (2023-05-28T22:04:08Z)
Readout of a quantum processor with high dynamic range Josephson parametric amplifiers [132.67289832617647]
Device is matched to the 50 $Omega$ environment with a bandwidth of 250-300 MHz, with input saturation powers up to -95 dBm at 20 dB gain. A 54-qubit Sycamore processor was used to benchmark these devices. Design has no adverse effect on system noise, readout fidelity, or qubit dephasing.
arXiv Detail & Related papers (2022-09-16T07:34:05Z)
Topological Josephson parametric amplifier array: A proposal for directional, broadband, and low-noise amplification [39.58317527488534]
Low-noise microwave amplifiers are crucial for detecting weak signals in fields such as quantum technology and radio astronomy. We show that compact devices with few sites can achieve exceptional performance, with gains exceeding 20 dB over a bandwidth ranging from hundreds of MHz to GHz. The device also operates near the quantum noise limit and provides topological protection against up to 15% fabrication disorder.
arXiv Detail & Related papers (2022-07-27T18:07:20Z)
Deep Learning-Based Synchronization for Uplink NB-IoT [72.86843435313048]
We propose a neural network (NN)-based algorithm for device detection and time of arrival (ToA) estimation for the narrowband physical random-access channel (NPRACH) of narrowband internet of things (NB-IoT) The introduced NN architecture leverages residual convolutional networks as well as knowledge of the preamble structure of the 5G New Radio (5G NR) specifications.
arXiv Detail & Related papers (2022-05-22T12:16:43Z)
End-to-End Multi-speaker Speech Recognition with Transformer [88.22355110349933]
We replace the RNN-based encoder-decoder in the speech recognition model with a Transformer architecture. We also modify the self-attention component to be restricted to a segment rather than the whole sequence in order to reduce computation.
arXiv Detail & Related papers (2020-02-10T16:29:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.