Neural networks for a dynamic decoupling of a nonlinear MIMO dynamic plant

In the paper a method of synthesis of a neural controller which goal is to reduce effects of coupling of the nonlinear multi-input multi-output (MIMO) plant inputs and outputs is presented. The designed neural controller contains a set of neural nets that determine values of parameters of linear decoupling controllers calculated for the adopted nonlinear plant model at its operating points. A known dynamic decoupling technique is used to generate training and evaluation data for the synthetized neural nets. The resulting neural (gain-scheduling) controller varies its parameters depending on the current plant operating point.