基于社会学习机制的改进人工鱼群算法

Improved artificial fish swarm algorithm based on social learning mechanism

针对人工鱼群算法后期搜索速度慢、不易得到精确解等问题,结合社会学习机制提出一种改进算法。当人工鱼群算法进行到优化后期时,使用群体社会学习机制中的趋同和趋异行为进行寻优。两种行为搜索速度快,寻优精度高,且趋异现象提高了群体的多样性,增强了跳出局部极值的能力,在一定程度上改善了原算法的搜索性能。仿真实验结果表明了改进算法的可行性和有效性。

The Artificial Fish Swarm Algorithm （AFSA） has low search speed and it is difficult to obtain accurate value. To solve the problems, an improved algorithm based on social learning mechanism was proposed. In the latter optimization period, the authors used convergence and divergence behaviors to improve the algorithm. The two acts had fast search speed and high optimization accuracy, meanwhile, the divergence behavior enhanced the population diversity and the ability of skipping over the local extremum. To a certain extent, the improved algorithm enhanced the search performance. The experimental results show that the proposed algorithm is feasible and efficacious.