Non-fragile robust finite-time stabilization for nonlinear stochastic systems via neural network

This paper deals with the problem of non-fragile robust finite-time stabilization for a class of uncertain nonlinear stochastic systems via neural network. First, applying multilayer feedback neural networks, the nonlinearity is approximated by linear differential inclusion under state-space representation. Then, a sufficient condition is proposed for non-fragile state feedback finite-time stabilization in terms of matrix inequalities. Furthermore, the problem is reduced to an optimization problem under the constraint of linear matrix inequality, and the corresponding solving algorithm is given. Finally, an example is given to illustrate the effectiveness of the developed method.