Deep Learning-Driven Inverse Design of Doherty Power Amplifiers Using Pixelated Combiners and Dual-State Impedance Synthesis
This work addresses the challenging design of Doherty PA combiners for RF engineers, offering an automated inverse design approach with demonstrated high performance.
The paper proposes a deep learning-driven inverse design methodology for Doherty power amplifier combiners using CNNs, pixelated layouts, and genetic algorithms. Two prototypes achieve >44.2 dBm saturated output power, >71.2% peak drain efficiency, and 64% efficiency at 6-dB back-off, with ACLR better than -51.3 dBc after digital predistortion.
The output combiner of a Doherty power amplifier (PA) integrates load modulation, impedance matching, and phase compensation within a single network, making its design and synthesis highly challenging. In this paper, we propose a three-port Doherty combiner design methodology that combines deep convolutional neural networks (CNNs), pixelated layout representations, and genetic algorithms (GA) with dual-state impedance synthesis to address both peak and back-off power conditions. As a proof of concept, two GaN HEMT Doherty PA prototypes incorporating three-port pixelated combiners are designed and fabricated. Both prototypes achieve a measured saturated output power exceeding 44.2 dBm with peak drain efficiency above 71.2% within 2.6-2.8 GHz. Furthermore, a drain efficiency as high as 64% is measured at the 6-dB back-off level. After applying digital predistortion, each prototype achieves an adjacent channel leakage ratio (ACLR) better than -51.3 dBc.