Event‐triggered H∞$$ {H}_{\infty } $$ performance state estimation for neural networks with time‐varying delay.

The issue of event‐triggered H∞$$ {H}_{\infty } $$ performance state estimation for neural networks with time‐varying delays is addressed in this paper. An innovative event‐triggered approach is presented, designed to strike a harmonious equilibrium between the state estimator's performance and the communication bandwidth of the network. The proposed approach captures the relationship between the time‐varying delay and system states by employing a delay derivative‐dependent integral inequality with matrices that account for delay derivatives. This novel formulation ensures the asymptotic stability of the estimation error system, thereby fulfilling the H∞$$ {H}_{\infty } $$ performance requirement. The desired event‐triggered estimators are then obtained through the use of linear matrix inequalities. The effectiveness of this approach is demonstrated through a numerical example. [ABSTRACT FROM AUTHOR]