结合文化算法的多种群协同变异PSO算法  

Particle swarms cooperative mutative optimization algorithm combining cultural algorithm

作　　者：郭骥[1] 彭鑫[1] 马林华[1] 

机构地区：[1]空军工程大学工程学院,西安710038

出　　处：《计算机工程与应用》2011年第16期46-48,96,共4页Computer Engineering and Applications

摘　　要：粒子群算法是一种新的基于群体智能的启发式全局优化算法,其概念简单,易于实现,而且具有良好的优化性能,目前已在许多领域得到应用。但在求解高维多峰函数寻优问题时,算法易陷入局部最优。结合文化算法和高斯变异的思想,提出一种基于文化算法和高斯变异的多群协同粒子群算法。该算法可以摆脱局部最优解对微粒的吸引,基于典型高维复杂函数的仿真结果表明,与多种群粒子群优化算法相比,该混合算法具有更好的优化性能。Particle Swarm Optimization（PSO） is a new heuristic global optimization algorithm based on swarm intelligence.The algorithm is simple,easy to implement and has good performance of optimization.Now it has been applied in many fields.However,when optimizing multidimensional and multimodal functions,the basic particle swarm optimization is apt to be trapped in local optimum.Combing with cultural algorithm and Gaussian mutation,an improved particle swarms cooperative optimization algorithm is presented.This modified version can break away from the attraction of the local optimal solution.Simulation results on benchmark complex functions with high dimension show that this algorithm performs better than the basic particle swarms cooperative optimization algorithm.

关 键 词：文化算法 高斯变异 粒子群算法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]