Using an ANN Approach to Estimate Output Power and PAE of A Modified Class-F Power Amplifier

In this paper, an efficient Class-F power amplifier (PA) is designed, simulated and modeled. This type of amplifier has nonlinear behaviors and uses tuning and controlling harmonics as the most important mechanism to increase efficiency. Feedforward artificial neural network (ANN) model is proposed to predict and estimate the nonlinear output of the power amplifier. The designed amplifier operates at 900 MHz, with 18 dB gain and 70 %Power-Added Efficiency (PAE). In the design process, the artificial neural network model is used to predict PAE and output power parameters as a function of input power, drain voltage and gate voltage of the applied transistor (DC Biasing voltages). The obtained mean relative errors (MREs) are less than 0.03% and 0.09% for the predicted output power and PAE parameters.