Neural-Network-Based Nonlinear Adaptive Dynamical Decoupling Control

In this letter, a nonlinear adaptive dynamical decoupling control algorithm using neural networks (NNs), a novel technique, is proposed for a class of uncertain nonlinear multivariable discrete-time dynamical systems. By combining open-loop decoupling compensation and generalized minimum variance adaptive scheme with NNs, complete dynamical decoupling is realized. The algorithm is applicable to the systems which are open-loop unstable and nonminimum phase in a neighborhood of the origin Xi. In the domain Xi, it can assure the bounded-input-bounded-output (BIBO) stability of the closed-loop system and can also make the generalized tracking error converge to a neighborhood of zero, whose size is evaluated and depends on the approximation error of the NN. Theory analysis and simulation results are presented to show the effectiveness of the proposed method