H∞ State Estimation for Neural Networks With General Activation Function and Mixed Time-Varying Delays

This article deals with H-infinity state estimation of neural networks with mixed delays. In order to make full use of delay information, novel delay-product Lyapunov-Krasovskii functional (LKF) by using parameterized delay interval is first constructed. Then, generalized free-weighting-matrix integral inequality is used to estimate the derivative of LKF to reduce the conservatism. Also, a more general activation function is further applied by combining with parameterized delay interval in order to obtain a more accurate estimator model. Finally, sufficient conditions are derived to confirm that the estimation error system is asymptotically stable with a prescribed H-infinity performance. Numerical examples are simulated to show the benefits of our proposed method.

Automated summary

This article presents a method for H-infinity state estimation of neural networks with mixed delays, utilizing novel delay-product Lyapunov-Krasovskii functional with parameterized delay interval. By applying generalized free-weighting-matrix integral inequality and a more general activation function, a more accurate estimator model is obtained. The sufficient conditions derived confirm the asymptotic stability of the estimation error system with prescribed H-infinity performance.