摘要: Gaussian particle swarm optimization (GPSO) algorithm has shown promising results for solving multimodal problems in low dimensional search space. But similar to evolutionary algorithms (EAs), GPSO may also get stuck local minima when optimizing functions with many like the Rastrigin or Riewank high In this paper, an approach which consists of a jumps escape from is presented. The jump strategy implemented as mutation operator based on and Cauchy probability distribution. new was tested suite well-known benchmark optima were compared those obtained by standard PSO algorithm, constriction factor. Simulation show that outperforms one presents very competitive performance factor self-adaptive programming.