Abstract: This paper proposes a new adaptive particle swarm optimization algorithm with mutation operator.It contains a new adaptive inertia weight so as to access to local search quickly at the front of the iteration.Based on the adaptive variance and meandist of the swarm，we have judged whether the algorithm sinks into the local minimum or not，then we have used new mutation operator for some swarms so as to escape from the local minimum’s basin of attraction and realized global search.The experiments on six problems show that the modified algorithm can improve the global search ability and greatly enhance the successful rate of search.

Key words: Particle Swarm Optimization, inertia weight, global adaptive standard deviation, mutation operator

摘要： 提出了一种新的带有变异算子的自适应粒子群优化算法，该算法使用了一种新的自适应惯性权重，使得算法在迭代的早期快速进人局部搜索，并且根据群体的适应度方差和平均聚集距离来判断算法在迭代的后期是否陷入局部最优点陷阱，对群体中的部分粒子采用新构造的变异运算作用，从而摆脱局部搜索的束缚，以实现全局搜索的性能。通过对六个例子的测试，表明这种改进的PSO算法的全局搜索能力和搜索成功率有较大提高。

关键词: 粒子群优化, 惯性权重, 整体适应度标准差, 变异算子