Decentralized event-triggered adaptive neural network control for nonstrict-feedback nonlinear interconnected systems with external disturbances against intermittent DoS attacks.

• This paper aims to construct a NN DETAC scheme for interconnected nonlinear system against Dos attacks and external disturbances. • A switching-type adaptive state observer with a disturbance estimation value is proposed and an anti-disturbance decentralized event-triggered adaptive control scheme is developed. The proposed method can enhance system anti-disturbance ability. • Different from the sampled-data control scheme in the related literature, the NN DETAC scheme is developed, which can efficiently save communication resources. • By employing the properties of the hyperbolic tangent function, the interconnection terms no longer meet the global Lipschitz conditions, which relaxes the constrain condition. This paper discusses the issue of decentralized event-triggered adaptive neural network (NN) control for nonstrict-feedback nonlinear interconnected systems with external disturbances and intermittent denial-of-service (DoS) attacks. In the presence of DoS attack, all state variables are not used to design a feedback controller via the standard backstepping method. To solve this problem, a novel switching-type adaptive state observer with a disturbance compensation is constructed, where the disturbance compensation is obtained via constructing a disturbance observer. A decentralized event-triggered adaptive controller is designed by using the backstepping method to weaken the influences of DoS attack and the waste of communication resources, where a first-order sliding mode differentiator is introduced to prevent the "calculation explosion". By using linear matrix inequality techniques, some solvable sufficient conditions are attained to derive the observer gain. The closed-loop system is proved to be stable via the improved average dell time method and the piecewise Lyapunov stability theories. This control scheme ensures that all closed-loop signals remain bounded. Finally, simulation results are utilized to demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]