Study of Neural Network Control Stability Based on Mixed Linear Integer Programming

The use of a neural network controller as a control system for a nonlinear plant is one of the main directions of development of modern control theory. In this paper we develop an approach based on the synthesis of the Lyapunov neural network function together with the regulator, which will ensure the stability of the feedback control system. It is shown that the search for the Lyapunov neural network function can be represented as a solution to the mixed integer linear programming problem, for which effective solvers have been developed.