Behavioral Modeling of Power Amplifiers With Dynamic Fuzzy Neural Networks

Abstract

In this letter, dynamic fuzzy neural networks (D-FNN) are applied to model power amplifiers (PAs) with memory effects. The D-FNN model implements Takagi-Sugeno-Kang (TSK) fuzzy systems based on extended radial bias function (RBF) neural networks. The parameters of the model are trained by the online self-organized learning algorithm, in which the neurons can be recruited or deleted dynamically according to their significance to system performance, and the over fitting or over training problems can be avoided. The D-FNN model is validated in our test bench in which a Doherty PA is excited with 10 MHz and 20 MHz worldwide interoperability for microwave access (WiMAX) signals. Experimental results show that the D-FNN model can give an accurate approximation to characterize the wideband PAs with memory effects.