Resumen:
Data-driven control is a methodology that attempts to find a suitable controller, based only on data taken from the system. Within this method, the virtual reference feedback tuning (VRFT), is a one-shot data-driven approach that transforms the control problem into an identification problem using restricted complexity controllers. However, how to choose the number of parameters, or the relation between them is a subject that often is left apart. In this paper, the VRFT framework is applied to an alternate two-degrees-of-freedom (2DoF) structure and a¿ covariance test¿ is used in order to find the number of parameters needed. As it was expected, this test shows that the number of parameters is dependent on the way the controller is parameterized. A numerical example is shown at the end of the paper.
