基于混沌和差分进化的混合蝙蝠算法

Hybrid bats algorithm based on chaos and differential evolution

提出一种基于混沌和差分进化的混合蝙蝠优化算法.把基于Logistic映射的混沌序列引入到种群初始化中,在算法迭代过程中,通过一种早熟判断机制,对早熟的粒子进行差分进化算法的交叉、变异和选择操作,增强算法的多样性和全局寻优能力,有效避免陷入局部最优.通过8个标准测试函数的仿真结果表明,改进后的算法可以有效提高收敛精度和收敛速度.

A hybrid bat optimization algorithm is presented based on chaos and differential evolution, and the chaotic sequence is introduced into the population initialization on the basis of Logistic mapping. In the iterative process of this algorithm, the crossover, mutation, and selection operations of differential evolu- tion algorithm are carried out for the precocious particles based on a premature judgment mechanism, so that the variety and global optimization ability of the algorithm are enhanced and the local optimum is avoi- ded effectively. Finally, it is shown by the result of simulation of eight benchmark functions that the con- vergence accuracy and speed can be effectively improved by using the improved algorithm.