Improved Generalized H2 Filtering for Static Neural Networks with Time-Varying Delay via Free-Matrix-Based Integral Inequality

This paper focuses on the generalized H-2 filtering of static neural networks with a time-varying delay. The aim of this problem is to design a full-order filter such that the filtering error system is globally asymptotically stable with guaranteed H-2 performance index. By constructing an augmented Lyapunov-Krasovskii functional and applying the free-matrix-based integral inequality to estimate its derivative, an improved delay-dependent condition for the generalized H-2 filtering problem is established in terms of LMIs. Finally, a numerical example is presented to show the effectiveness of the proposed method.