提出一种基于改进粒子群动态搜索算法的网络重构方法，算法把初始粒子群按照适应度的大小分为两个互不交叉，且具有不同分工的子群，并进行动态搜索。通过引入了交叉和禁忌思想，减少了解陷入局部最优的可能性．与遗传、禁忌搜索算法重构的结果进行比较，表明本文算法具有更高的搜索效率，更容易找到全局最优解．-：An improved method based on improved particle swarm optimization dynamic search algodthm networkrcconfiguration

is　presented in this paper．The initial particle swarm is divided into two different subgroups according to the size of fitness，with a division of labour between the different subgroups of dynamic search．Cross

thinking and ideological tabu ale ledinto this algorithm to reduce the possibility of local Optimum．Compared with genetic and tabu search algorithm,the results show that the proposed method possesses a hi．gher search efficiency andis easier tO find the global optimum solutions．