关键词: 粒子群优化, 惯性权重, 变异

Abstract: For complex functions with high dimensions，standard particle swarm optimization methods are slow speed on convergence and easy to be trapped in local optimum.This paper proposes an inertia weight function，which can balance global and local search ability，fasten convergence speed，and by adding the mutation operation to the algorithm in the later phase，this algorithm improves the ability to break away from the local optimum solutions effectively.Experimental results on three typical complex functions with high dimensions show that the modified algorithm can rapidly converge at high quality solutions.

Key words: particle swarm optimization, inertia weight, mutation