Nonlinear Multivariable Predictive Control: Neural versus First Principle Modelling Approach

A neural network predictive control scheme is compared with a first principle model predictive control strategy when controlling a three tanks system. The neural network approach involves a recurrent Elman network for capturing the plant’s dynamics being the learning stage implemented on-line using a modified version of the back-propagation through time algorithm. In the first principle model predictive control scheme a realtime open-loop linear constrained optimisation problem is solved with a standard quadratic programming algorithm. Experimental results collected from the non-linear plant are presented.