中文摘要：

粒子群在搜索过程中容易陷入局部而无法找到全局最优值,为了解决此早熟问题,提出基于函数变换的改进混沌粒子群优化算法。此方法将Logistic映射和改进的Tent映射引入到粒子群中代替随机数;将函数变换引入到粒子的速度、位置更新过程中以凸显全局最优值与局部极优值的差异,从而使粒子跳出局部极优值点,加细搜索进而找到全局最优值点。数值实验表明,基于函数变换的改进混沌粒子群在搜索时间和效率上要优于标准粒子群和基于Logistic映射的混沌粒子群。改进的算法是可行而有效的。

英文摘要：

Particle swarm optimization was easily trapped by the local optima and failed to find the global optima.To solve this premature problem,introduced the logistic map and the improved Tent map into the PSO to replace the randomness.Applied function transform to refine the searching in the updating process of particle velocity and particle position.The difference between the local optima and global optima is more obvious,which leads the particle jump out the trap and find the global optima.The numerical experiment shows that the chaotic PSO based on improved Tent map has a better searching result than the standard PSO and chaotic PSO based on logistic map.And the improved algorithm is feasible and effective.