Decoupling of a class of nonlinear discrete time systems using neural networks

In this paper, the decoupling problem for a class of nonlinear discrete time systems is considered. A necessary and sufficient condition for the solvability of the decoupling problem for a class of discrete time systems is given. It is also shown that if the decoupling problem is solvable, the modified systems can be linear. Based on the result, a strategy for realizing decoupling using neural networks is proposed. Simulation in this paper supports the authors´ theory and the decoupling strategy