A D-Band InP Power Amplifier Featuring Fully AI-Generated Passive Networks

This work presents a high-efficiency D-band power amplifier (PA) implemented in 250nm InP technology. A key innovation is the integration of artificial intelligence (AI) into the RFPA design flow for the automated generation of passive networks. By utilizing a machine learning (ML) model as a surrogate for time-consuming electromagnetic (EM) solvers, this approach explores broader design space, uncovers potentially non-intuitive structures and improves productivity. The physics-augmentation in the ML model mitigates its dependance on big training dataset, achieving an S-parameter prediction error of less than 0.5 dB at the target frequency of 130 GHz. This ML-assisted designed PA delivers a saturated output power (Psat) of 15.3 dBm and a peak power-added efficiency (PAE) of 26%. Additionally, it achieves a peak gain of 12.7 dB, a 3 dB bandwidth spanning 110 GHz to 140 GHz, and demonstrates its capability to support high-order QAM signals at tens of Gb/s data rates.