基于混沌搜索与种群交叉的粒子群优化算法

Particle Swarm Optimization Algorithm Based on Chaotic Searching and People Crossover Operator

在种群交叉粒子群算法优化中,为克服粒子群优化算法进化后期收敛速度慢、易陷入局部最优等缺点,提出一种基于逻辑自映射函数的混沌搜索与种群交叉的粒子群优化算法。算法中每进化一次粒子搜索四次:一次全局搜索,一次局部搜索,一次向局部搜索学习的搜索,一次交叉重组搜索,搜索完成后分别进行三角函数学习,以增加种群的多样性。四个经典基准测试函数仿真结果表明,改进的粒子群优化算法在收敛速度和寻优精度上均有提高,与现有的改进粒子群优化算法相比,改进优化算法具有明显的优势。

In order to overcome the drawbacks that Particle Swarm Optimization （PSO） converges slowly at the last stage and easily falls into local minima,this paper proposed a new PSO optimization algorithm utilizing one chaot- ic searching operator based on self - logical mapping function and population crossover operator. The algorithm of ev- ery evolutionary particle search four times： a global search, a local search, a search which learns form local search, and a cross restructuring search. After the completion of the search, The particles learn trigonometric function respec- tively, in order to increase the diversity of population. Four classic benchmark test function simulation results show that the improved particle swarm optimization algorithm can increase the convergence speed and improve the optimi- zing accuracy, compared with the existing improved particle swarm optimization algorithm.