An Event-Triggered Approach to H∞ State Estimation for Neural Networks with Time-Varying Delays

This paper investigates event-triggered
$H_{\infty}$
performance state estimation problem for neural networks model with time-varying delays. A novel event-triggered scheme (ETS) introducing the estimation error is designed, which is a tradeoff between the state estimator performance and network communication bandwidth in accordance with practical requirement. A Wirtinger-type free-matrix-based integral inequality (WFMBII) is put forward, in which some delay-product-type matrices are produced to fully link the relationship among time-varying delay and system states. On these basis, sufficient condition is builded to guarantee the estimation error system to be is bounded and satisfies the
$H$
∞ performance requirement. Meanwhile, the desired event-triggered estimators are solved by linear matrix inequalities (LMIs). A numerical example is given to illustrate the correctness of the obtained method.