Deep Learning-Driven Black-Box Doherty Power Amplifier with Pixelated Output Combiner and Extended Efficiency Range
arXiv:2603.16565v2 Announce Type: replace-cross Abstract: This article presents a deep learning-driven inverse design methodology for Doherty power amplifiers (PA) with multi-port pixelated output combiner networks. A deep convolutional neural network (CNN) is developed and trained as an electromagnetic (EM) surrogate model to accurately and rapidly predict the S-parameters of pixelated passive networks. By leveraging the CNN-based surrogate model within a blackbox Doherty framework and a genetic algorithm (GA)-based optimizer, we effectively synthesize complex Doherty combiners that enable an
The increasing demands for efficiency in radio frequency systems, particularly in communications and sensing, are driving innovation in power amplifier design at the intersection of AI and hardware.
This development indicates a significant advancement in leveraging deep learning for complex RF circuit design, potentially leading to more efficient and powerful wireless communication systems.
The ability to rapidly design complex, high-efficiency power amplifiers using AI-driven inverse design methodologies could accelerate hardware development cycles and improve performance benchmarks for wireless devices.
- · Telecommunications companies
- · RF chip manufacturers
- · Deep learning hardware designers
- · Energy-efficient device developers
- · Traditional RF design methodologies
- · Hardware developers without AI integration
AI-designed power amplifiers will become more common, improving energy efficiency and performance of wireless devices.
This could lead to a competitive advantage for companies that integrate AI into their RF hardware design workflows, potentially centralizing expertise.
The methodology might extend to other complex hardware design challenges, accelerating innovation across various engineering domains and contributing to more efficient compute infrastructure.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI