Extrapolation of Load-Pull Data: A Novel Use of GAN Artificial Intelligence Image Completion
Austin Egbert, Charles Baylis, Robert J. Marks
Abstract
Amplifier design, both in traditional approaches and real-time circuit optimization, greatly benefits from fast and thorough extraction of information from measurement data. Using only a few performance samples at varying impedances, deep learning image completion techniques can be utilized to extrapolate an entire set of Smith chart load-pull contours. In addition to speeding nonlinear device characterizations, this extrapolation can be performed in an iterative fashion for use as a circuit optimization algorithm with a very low number of measurements. The techniques of this work have been tested in the measurement of a nonlinear, large-signal amplifier. The load impedance can be estimated with a typical error of < 0.1 linear units using as few as seven impedances and yields even better accuracy with larger sample sizes.