Abstract
A new particle swarm optimization (PSO) algorithm having a chaotic Hopfield Neural Network (HNN)
structure is proposed. Particles exhibit chaotic behaviour before converging to a stable fixed point which
is determined by the best points found by the individual particles and the swarm. During the evolutionary
process, the chaotic search expands the search space of individual particles. Using a chaotic system to
determine particle weights helps the PSO to escape from the local extreme and find the global optimum.
The algorithm is applied to some benchmark problems and a pressure vessel problem with nonlinear
constraints. The results show that the proposed algorithm consistently outperforms rival algorithms by
enhancing search efficiency and improving search quality