Tracking Synchronization of Coupled Non-identical Neural Networks Via Iterative Learning Control

Abstract

This article focuses on the tracking synchronization of the coupled non-identical neural networks. A kind of D-type iterative learning control (ILC) is proposed and the control input of each agent is updated iteratively such that tracking synchronization can be achieved under a repetitive environment. In addition, by virtue of the contraction mapping principle, some sufficient criteria for guaranteeing the tracking synchronization are established under the structurally fixed signed digraph. Finally, a numerical example is provided to demonstrate the viability of the theoretical results.