Double center swarm exploring varying parameter neurodynamic network for non-convex nonlinear programming
Zhijun Zhang, Ming Zhu, Xiaohui Ren
Abstract
To solve non-convex nonlinear programming problems, a double center swarm exploring varying parameter neurodynamic network (DCSE-VPNN) is proposed and analyzed. Firstly, a varying parameter neurodynamic network is proposed as a solver for nonlinear programming to seek local optimal solutions. Secondly, a double center particle swarm optimization algorithm is exploited, wherein each neural network serves as a particle. Each particle independently explores a local optimal solution. Through information exchange among particles, the subsequent positions to be explored are updated. As a result, DCSE-VPNN acquires the capability of global search. Computer simulation experiments verify the efficacy of the proposed approach in solving non-convex nonlinear programming problems. In comparison with two existing methods, the results show that the proposed DCSE-VPNN approach has fewer iterations and higher search accuracy.