Neural networks based minimal or reduced model representation for control of nonlinear MIMO systems

This paper raises the issue of finding reduced/ minimal state-space form for MIMO systems based on neural networks. Two cases are studied: when system is given as a “black-box” model and when order of the controlled system is known a priori. Modified structure of the standard NN-ANARX (Additive Nonlinear AutoRegressive with eXogenous inputs based on Neural Networks ) allows to eliminate all reduced interconnections between neurons and thus to get the minimal state-space representation in second case. If we deal with unknown dynamical system then we reduce model and find optimal structure of the neural network automatically using genetic algorithm. After the model was found parameters of the NN can be used to design a state controller for the control of nonlinear MIMO systems using the linearization feedback.