一种带交叉因子的双向寻优粒子群优化算法

针对传统粒子群算法易早熟、精度低、后期收敛速度慢等问题,结合反向学习理论,提出了一种基于交叉因子的双向寻优粒子群优化算法(CBMPSO)。该算法使初始种群在搜索区域均匀分布,计算粒子及其反向粒子的适应值,取最优作为初始种群;迭代过程增加对全局最差粒子的跟踪,随机开启基于交叉因子的双向学习机制。对几种典型函数的测试结果表明,CBMPSO算法的寻优能力及收敛速度有了显著提高,并且能够有效避免早熟收敛问题。

Particle swarm optimization of corro-factor andbilingual learning mechanism

To overcome the disadvantages of particle swarm optimization PSO algorithm such as premature, bad convergence rate, this paper presented an improved algorithm CBMPSO. The algorithm first made the initial population in the searching space evenly distributed, then calculated the initial and the opposite ones' fitness value, chose the better ones as the initial population. Added global poorest position to the update of particle position and started corro-factor and bilingual learning Mechanism randomly. The numeric experiments indicate that the new strategy can not only speed up the convergence but also can avoid the premature convergence problem effectively.