An improved particle swarm optimization

Abstract

The basic and improved algorithms of PSO are focused on how to search effectively the optimalsolution in the solution space by using one of the particle swarm. However, the particles are always chasing the global optimal point and such points are currently found on their way of search, rapidly leading their speed down to zero and hence being restrained in the local minimum. Consequently, there are the convergence or early maturity of particles. The improved PSO is based on the enlightenment of Back-Propagation (BP) neural network while the improvement is similar to the smooth weight through low-pass filter. The test of classical functions show that the PSO provides a promotion in the convergence precision and make better a certain extent in the calculation velocity.