Non-fragile memory H ∞ control for uncertain delayed neural networks via a robust gain-scheduling method

This work deals with the non-fragile memory H ∞ control issue for a class of uncertain delayed neural networks with randomly occurring time-varying parameters uncertainties and controller gain fluctuations. These random variables are supposed to be satisfy certain Bemoulli distributed white noise sequences, which are mutually uncorrelated stochastic variables. The main purpose of this work is to design a desired non-fragile memory H ∞ control law to ensure the asymptotical stability of the closed-loop system with the guaranteed H ∞ disturbance attenuation level. A robust gain-scheduling method is employed to tackle the addressed problem where the designed controller gains are dependent on certain parameters of practical significance. By using stochastic analysis, delayed segmentation technique and Lyapunov-Krasovskii functional approach, an optimized control algorithm is designed for the existence of the desired non-fragile memory feedback controller. Finally, two numerical examples are presented to demonstrate the superiority and applicability of the theoretical results.