NLq neural control theory: Case study for a ball and beam system
H. Verreist, Karel Van Acker, Johan A. K. Suykens, B. Motmans, Bart De Moor, Joos P. L. Vandewalle · 1997
In this paper we design a linear dynamic output feedback controller for a ball and beam system based on an identified neural state space model. This is done by applying dynamic backpropagation, constrained by NLqinternal or I/O stability conditions. The performance of the controller has been tested on a real ball and beam set-up.