D. Schreurs (Belgium), A. Beyer (Germany), and B. Nauwelaers (Belgium)
artificial neural networks – large-signal modelling – time domain techniques – identification – dynamic modelling
We present a methodology to construct behavioural models for microwave devices from time-domain large signal measurements. The behavioural model for the considered class of devices (microwave transistors) is defined by expressing the terminal currents as function of the state variables, being the terminal voltages and their higher order time derivatives. In this work, we show that artificial neural networks (ANNs) are valuable candidates to represent these relationships. They outperform models based on multivariate polynomials, because ANNs can better represent the typical physical characteristics of the considered devices.
Important Links:
Go Back
