Improved results on solving convex programming problems with delayed Lagrangian neural networks

Abstract

This paper is concerned with the stability analysis problem of a delayed Lagrangian neural network designed for solving nonlinear programming problems with linear equality constraints. By constructing a new Lyapnuov-Krasovskii functional and employing the free-weighting matrix method, a less conservative delay-dependent stability criterion is established in terms of linear matrix inequalities (LMIs). Finally, an example is given to illustrate the effectiveness of our proposed method.