Design and analysis of an efficient neural network model for solving nonlinear optimization problems

作     者：Da Silva, IN Do Amaral, WC De Arruda, LV 

作者机构：UNESP Sao Paulo State Univ Dept Elect Engn CP 473 BR-17033360 Bauru SP Brazil 

出 版 物：《INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE》 (国际系统科学杂志)

年 卷 期：2005年第36卷第13期

页      面：833-843页

核心收录：

学科分类：1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：constrained optimization problems recurrent neural networks Hopfield networks nonlinear programming 

摘      要：This paper presents an efficient approach based on a recurrent neural network for solving constrained nonlinear optimization. More specifically, a modified Hopfield network is developed, and its internal parameters are computed using the valid-subspace technique. These parameters guarantee the convergence of the network to the equilibrium points that represent an optimal feasible solution. The main advantage of the developed network is that it handles optimization and constraint terms in different stages with no interference from each other. Moreover, the proposed approach does not require specification for penalty and weighting parameters for its initialization. A study of the modified Hopfield model is also developed to analyse its stability and convergence. Simulation results are provided to demonstrate the performance of the proposed neural network.