关键词: 区间二次规划, 神经网络, 增广拉格朗日函数, Lyapunov函数

Abstract: In this paper, based on neural network, an approach of solving interval quadratic programming problems with linear constraints is proposed. By using augmented Lagrange function, a neural network for solving quadratic programming is presented. Based on Saddle point theorem, the equilibrium point of the proposed neural network is proved to be equivalent to the optimal solution of the interval quadratic programming problems. The global exponential stability of the proposed neural network is analyzed in terms of a Lyapunov approach. Two illustrative examples are provided to illustrate the usefulness and the efficiency of the theoretical results.

Key words: interval quadratic programming, neural network, augmented lagrange function, lyapunov function