Decentralized Stabilization of Neural Network Linearly Interconnected Systems via T-S Fuzzy Control

Abstract

The stabilization problem is considered in this study for a neural-network (NN) linearly interconnected system that consists of a number of NN models. First, a linear difference inclusion (LDI) state-space representation is established for the dynamics of each NN model. Then, based on the LDI state-space representation, a stability criterion in terms of Lyapunov’s direct method is derived to guarantee the asymptotic stability of closed-loop NN linearly interconnected systems. Subsequently, according to this criterion and the decentralized control scheme, a set of Takagi-Sugeno (T-S) fuzzy controllers is synthesized to stabilize the NN linearly interconnected system. Finally, a numerical example with simulations is given to demonstrate the concepts discussed throughout this paper.