一种混合拟态物理学优化算法

A Hybird Artificial Physics Optimization Algorithm

在拟态物理学优化算法中,群体中所有个体都采用相同的作用力规则来产生后代,所有个体均表现出相同的搜索特征,使算法的种群多样性较差。借鉴物理学中不同环境下个体之间的物理规则不同,且遵循的运动规律亦不同,为算法迭代过程中不同的优化个体制定了不同的作用力规则,采用随机选择策略为不同个体动态分配不同的作用力规则,以增加种群多样性。然后用仿真实验验证了该混合拟态物理学优化算法的有效性。

In the physicomimetics or Artificial Physics Algorithm, all individuals in the group produce offsprings with the same force, and all individuals show the same search features, so the population diversity of the algorithm is poor. This paper takes example by individuals with different physical rules in different environment, and makes the different virtual force for different optimization individuals in the process of algorithm by following the different rules of movement, Adopting random selection strategy for different individual allocation different rules of these forces dynamically, the population diversity is increased. Finally, simulation experiments were used to verify the effectiveness of the optimization Hybird Artificial Physics algorithm.