Aperiodically Intermittent Control for Exponential Stabilization of Delayed Neural Networks Via Time-dependent Functional Method

In this paper, the exponential stabilization problem is investigated for delayed neural networks (DNNs) via aperiodically intermittent control. First, a suitable time-dependent functional is constructed in view of the features of intermittent control, which fully utilizes the state information on the working intervals. The main merit of the designed time-dependent functional lies in that the 'jump' behavior, at every switching point, between two Lyapunov functionals vanishes. It does not increase at the beginning of working intervals. Meanwhile, two sufficient linear matrix inequalities (LMIs)-based stability criteria are established in combination with some estimation techniques and Lyapunov stability theorem. On this basis, the work period, feedback control gain, and decay rate, can be jointly designed to achieve the exponential stabilization of networks by utilizing aperiodically intermittent controller. Finally, two simulation examples are developed to demonstrate the effectiveness of the derived theoretical results.