ADAPTIVE OUTPUT FEEDBACK CONTROL OF A SCALE HELICOPTER RESTRICTED TO A 2DOF PLATFORM

摘要

In this paper we present the application of the adaptive neural-networktechnique in (Calise, Hovakimyan and Idam, 2001) to the control of the 3DoF model helicopter in (Avila, Brogliato, Dzul and Lozano, 2003). The technique uses feedback linearization, linear (coarse) compensation and adaptive-neural-network (fine) compensation. The description of the technique is presented in a way as self-contained as possible. The helicopter model also includes a one-sided constraint to address take-off and landing, as well as hover. Our study shows that a very simple and poor plant model is adequate, and that the the neural network compensates this, completely on-line, without initial training.