一种新型的动态粒子群优化算法

为了改进标准粒子群优化算法全局搜索性能，提出了一种种群动态变化的多种群粒子群优化算法。当算法搜索停滞时，把种群分裂成2个子种群，通过子种群粒子随机初始化及个体替代机制增强种群多样性，两个子种群并行搜索一定代数后，通过混合子种群来完成不同子种群中粒子的信息交流。收敛性分析表明，本文算法能以概率1收敛到全局最优解。实验结果表明，本文算法具有较好的全局寻优能力和较快的收敛速度。

Novel dynamic particle swarm optimizer algorithm

In order to improve the standard particle swarm optimization algorithm global search performance, a novel particle swarm optimization algorithm with population dynamics was proposed. When the algorithm search stagnation, the population was divided into two sub-populations. Population diversity was obtained by using random initialization particles and alternative mechanisms of sub-populations in the period of two sub-populations parallel searching. after sub-populations parallel searching, the information of particle in the different sub-population was exchange by mixing two sub-population into one population. The convergence of proposed algorithm is analyzed and the results indicate that it can guarantee converge on the global minimum. The functional test shows that proposed algorithm has better global search ability and fast convergence speed.